fixed release version (#333)

* fixed release version

* update docs

docs/_modules/index.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Overview: module code &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Overview: module code &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/acer_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.acer_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.acer_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/actor_critic_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.actor_critic_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.actor_critic_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/agent_interface.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.agent_interface &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.agent_interface &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/bc_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.bc_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.bc_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/categorical_dqn_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.categorical_dqn_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.categorical_dqn_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/cil_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.cil_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.cil_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/clipped_ppo_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.clipped_ppo_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.clipped_ppo_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/ddpg_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.ddpg_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.ddpg_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/dfp_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.dfp_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.dfp_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/dqn_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.dqn_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.dqn_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/mmc_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.mmc_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.mmc_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/n_step_q_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.n_step_q_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.n_step_q_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/naf_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.naf_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.naf_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/nec_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.nec_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.nec_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/pal_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.pal_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.pal_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/policy_gradients_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.policy_gradients_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.policy_gradients_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/ppo_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.ppo_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.ppo_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/qr_dqn_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.qr_dqn_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.qr_dqn_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/rainbow_dqn_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.rainbow_dqn_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.rainbow_dqn_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/soft_actor_critic_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.soft_actor_critic_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.soft_actor_critic_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/agents/value_optimization_agent.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.agents.value_optimization_agent &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.agents.value_optimization_agent &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/architectures/architecture.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.architectures.architecture &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.architectures.architecture &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/architectures/network_wrapper.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.architectures.network_wrapper &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.architectures.network_wrapper &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/base_parameters.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.base_parameters &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.base_parameters &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/core_types.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.core_types &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.core_types &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/data_stores/nfs_data_store.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.data_stores.nfs_data_store &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.data_stores.nfs_data_store &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/data_stores/s3_data_store.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.data_stores.s3_data_store &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.data_stores.s3_data_store &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/environments/carla_environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.carla_environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.carla_environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/environments/control_suite_environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.control_suite_environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.control_suite_environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/environments/doom_environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.doom_environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.doom_environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/environments/environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/environments/gym_environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.gym_environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.gym_environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   
@@ -486,7 +486,6 @@
         <span class="bp">self</span><span class="o">.</span><span class="n">is_mujoco_env</span> <span class="o">=</span> <span class="s1">&#39;mujoco&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">is_roboschool_env</span> <span class="o">=</span> <span class="s1">&#39;roboschool&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="o">=</span> <span class="s1">&#39;Atari&#39;</span> <span class="ow">in</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="vm">__class__</span><span class="p">)</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">timelimit_env_wrapper</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span>
         <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">frameskip</span> <span class="o">=</span> <span class="mi">1</span>  <span class="c1"># this accesses the atari env that is wrapped with a timelimit wrapper env</span>
             <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env_id</span> <span class="o">==</span> <span class="s2">&quot;SpaceInvadersDeterministic-v4&quot;</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_skip</span> <span class="o">==</span> <span class="mi">4</span><span class="p">:</span>
@@ -588,12 +587,6 @@
             <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">native_rendering</span><span class="p">:</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">renderer</span><span class="o">.</span><span class="n">create_screen</span><span class="p">(</span><span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">,</span> <span class="n">image</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">*</span><span class="n">scale</span><span class="p">)</span>
 
-        <span class="c1"># measurements</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">timestep_limit</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">spec</span><span class="o">.</span><span class="n">timestep_limit</span>
-        <span class="k">else</span><span class="p">:</span>
-            <span class="bp">self</span><span class="o">.</span><span class="n">timestep_limit</span> <span class="o">=</span> <span class="kc">None</span>
-
         <span class="c1"># the info is only updated after the first step</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span><span class="p">)</span><span class="o">.</span><span class="n">next_state</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">state_space</span><span class="p">[</span><span class="s1">&#39;measurements&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">VectorObservationSpace</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">info</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span>
@@ -653,7 +646,7 @@
     <span class="k">def</span> <span class="nf">_restart_environment_episode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">force_environment_reset</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
         <span class="c1"># prevent reset of environment if there are ale lives left</span>
         <span class="k">if</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">is_atari_env</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">unwrapped</span><span class="o">.</span><span class="n">ale</span><span class="o">.</span><span class="n">lives</span><span class="p">()</span> <span class="o">&gt;</span> <span class="mi">0</span><span class="p">)</span> \
-                <span class="ow">and</span> <span class="ow">not</span> <span class="n">force_environment_reset</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">timelimit_env_wrapper</span><span class="o">.</span><span class="n">_past_limit</span><span class="p">():</span>
+                <span class="ow">and</span> <span class="ow">not</span> <span class="n">force_environment_reset</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">step</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">action_space</span><span class="o">.</span><span class="n">default_action</span><span class="p">)</span>
         <span class="k">else</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">state</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">env</span><span class="o">.</span><span class="n">reset</span><span class="p">()</span>

docs/_modules/rl_coach/environments/starcraft2_environment.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.environments.starcraft2_environment &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.environments.starcraft2_environment &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/additive_noise.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.additive_noise &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.additive_noise &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/boltzmann.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.boltzmann &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.boltzmann &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/bootstrapped.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.bootstrapped &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.bootstrapped &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/categorical.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.categorical &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.categorical &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/continuous_entropy.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.continuous_entropy &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.continuous_entropy &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/e_greedy.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.e_greedy &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.e_greedy &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/exploration_policy.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.exploration_policy &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.exploration_policy &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/greedy.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.greedy &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.greedy &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/ou_process.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.ou_process &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.ou_process &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/parameter_noise.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.parameter_noise &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.parameter_noise &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/truncated_normal.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.truncated_normal &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.truncated_normal &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/exploration_policies/ucb.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.exploration_policies.ucb &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.exploration_policies.ucb &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/attention_discretization.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.attention_discretization &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.attention_discretization &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/box_discretization.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.box_discretization &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.box_discretization &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/box_masking.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.box_masking &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.box_masking &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/full_discrete_action_space_map.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.full_discrete_action_space_map &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.full_discrete_action_space_map &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/linear_box_to_box_map.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.linear_box_to_box_map &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.linear_box_to_box_map &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/action/partial_discrete_action_space_map.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.action.partial_discrete_action_space_map &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.action.partial_discrete_action_space_map &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_clipping_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_clipping_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_clipping_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_crop_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_crop_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_crop_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_move_axis_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_move_axis_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_move_axis_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_normalization_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_normalization_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_normalization_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_reduction_by_sub_parts_name_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_reduction_by_sub_parts_name_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_reduction_by_sub_parts_name_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_rescale_size_by_factor_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_rescale_size_by_factor_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_rescale_size_by_factor_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_rescale_to_size_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_rescale_to_size_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_rescale_to_size_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_rgb_to_y_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_rgb_to_y_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_rgb_to_y_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_squeeze_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_squeeze_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_squeeze_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_stacking_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_stacking_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_stacking_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/observation/observation_to_uint8_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.observation.observation_to_uint8_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.observation.observation_to_uint8_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/reward/reward_clipping_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.reward.reward_clipping_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.reward.reward_clipping_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/reward/reward_normalization_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.reward.reward_normalization_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.reward.reward_normalization_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/filters/reward/reward_rescale_filter.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.filters.reward.reward_rescale_filter &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.filters.reward.reward_rescale_filter &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/backend/redis.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.backend.redis &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.backend.redis &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/episodic/episodic_experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.episodic.episodic_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.episodic.episodic_experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/episodic/episodic_hindsight_experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.episodic.episodic_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.episodic.episodic_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/episodic/episodic_hrl_hindsight_experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.episodic.episodic_hrl_hindsight_experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/episodic/single_episode_buffer.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.episodic.single_episode_buffer &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.episodic.single_episode_buffer &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/non_episodic/balanced_experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.non_episodic.balanced_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.non_episodic.balanced_experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/non_episodic/differentiable_neural_dictionary.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.non_episodic.differentiable_neural_dictionary &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.non_episodic.differentiable_neural_dictionary &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/non_episodic/experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.non_episodic.experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.non_episodic.experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/non_episodic/prioritized_experience_replay.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.non_episodic.prioritized_experience_replay &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.non_episodic.prioritized_experience_replay &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/memories/non_episodic/transition_collection.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.memories.non_episodic.transition_collection &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.memories.non_episodic.transition_collection &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/orchestrators/kubernetes_orchestrator.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.orchestrators.kubernetes_orchestrator &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.orchestrators.kubernetes_orchestrator &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_modules/rl_coach/spaces.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>rl_coach.spaces &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>rl_coach.spaces &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/_sources/index.rst.txt

@@ -27,7 +27,7 @@ Blog posts from the Intel® AI website:
 
 * `Release 0.11.0 <https://ai.intel.com/rl-coach-data-science-at-scale/>`_
 
-* Release 0.12.1 (current release)
+* Release 0.12.0 (current release)
 
 You can find more details in the `GitHub repository <https://github.com/NervanaSystems/coach>`_.
 

docs/_static/documentation_options.js

@@ -1,6 +1,6 @@
 var DOCUMENTATION_OPTIONS = {
     URL_ROOT: document.getElementById("documentation_options").getAttribute('data-url_root'),
-    VERSION: '0.12.1',
+    VERSION: '0.12.0',
     LANGUAGE: 'None',
     COLLAPSE_INDEX: false,
     FILE_SUFFIX: '.html',

docs/components/additional_parameters.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Additional Parameters &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Additional Parameters &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/imitation/bc.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Behavioral Cloning &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Behavioral Cloning &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/imitation/cil.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Conditional Imitation Learning &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Conditional Imitation Learning &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/index.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Agents &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Agents &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/other/dfp.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Direct Future Prediction &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Direct Future Prediction &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/ac.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Actor-Critic &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Actor-Critic &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/acer.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>ACER &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>ACER &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/cppo.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Clipped Proximal Policy Optimization &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Clipped Proximal Policy Optimization &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/ddpg.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Deep Deterministic Policy Gradient &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Deep Deterministic Policy Gradient &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/hac.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Hierarchical Actor Critic &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Hierarchical Actor Critic &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/pg.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Policy Gradient &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Policy Gradient &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/ppo.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Proximal Policy Optimization &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Proximal Policy Optimization &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/policy_optimization/sac.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Soft Actor-Critic &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Soft Actor-Critic &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/bs_dqn.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Bootstrapped DQN &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Bootstrapped DQN &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/categorical_dqn.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Categorical DQN &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Categorical DQN &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/double_dqn.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Double DQN &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Double DQN &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/dqn.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Deep Q Networks &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Deep Q Networks &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/dueling_dqn.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Dueling DQN &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Dueling DQN &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>
   
 
   

docs/components/agents/value_optimization/mmc.html

@@ -8,7 +8,7 @@
   
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
   
-  <title>Mixed Monte Carlo &mdash; Reinforcement Learning Coach 0.12.1 documentation</title>
+  <title>Mixed Monte Carlo &mdash; Reinforcement Learning Coach 0.12.0 documentation</title>