fixed release version (#333)

* fixed release version

* update docs

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>
   
 
   

docs/components/agents/value_optimization/n_step.html

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

docs/components/agents/value_optimization/naf.html

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

docs/components/agents/value_optimization/nec.html

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

docs/components/agents/value_optimization/pal.html

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

docs/components/agents/value_optimization/qr_dqn.html

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

docs/components/agents/value_optimization/rainbow.html

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