gryf/coach
1
0
Fork 0
mirror of https://github.com/gryf/coach.git synced 2025-12-18 19:50:17 +01:00
Code Issues Projects Releases Wiki Activity

TD3 (#338)

Browse Source
This commit is contained in:
Gal Leibovich
2019-06-16 11:11:21 +03:00
committed by GitHub
parent 8df3c46756
commit 7eb884c5b2
107 changed files with 2200 additions and 495 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
docs/_modules/rl_coach/agents/qr_dqn_agent.html
View File

@@ -196,7 +196,7 @@
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="kn">from</span> <span class="nn">copy</span> <span class="k">import</span> <span class="n">copy</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="k">import</span> <span class="n">Union</span>
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
@@ -262,6 +262,17 @@
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">return</span> <span class="n">actions_q_values</span>
<span class="c1"># prediction&#39;s format is (batch,actions,atoms)</span>
<span class="k">def</span> <span class="nf">get_all_q_values_for_states_and_softmax_probabilities</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">states</span><span class="p">:</span> <span class="n">StateType</span><span class="p">):</span>
<span class="n">actions_q_values</span><span class="p">,</span> <span class="n">softmax_probabilities</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="kc">None</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">exploration_policy</span><span class="o">.</span><span class="n">requires_action_values</span><span class="p">():</span>
<span class="n">outputs</span> <span class="o">=</span> <span class="n">copy</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">networks</span><span class="p">[</span><span class="s1">&#39;main&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">online_network</span><span class="o">.</span><span class="n">outputs</span><span class="p">)</span>
<span class="n">outputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">networks</span><span class="p">[</span><span class="s1">&#39;main&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">online_network</span><span class="o">.</span><span class="n">output_heads</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">softmax</span><span class="p">)</span>
<span class="n">quantile_values</span><span class="p">,</span> <span class="n">softmax_probabilities</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_prediction</span><span class="p">(</span><span class="n">states</span><span class="p">,</span> <span class="n">outputs</span><span class="p">)</span>
<span class="n">actions_q_values</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_q_values</span><span class="p">(</span><span class="n">quantile_values</span><span class="p">)</span>
<span class="k">return</span> <span class="n">actions_q_values</span><span class="p">,</span> <span class="n">softmax_probabilities</span>
<span class="k">def</span> <span class="nf">learn_from_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">):</span>
<span class="n">network_keys</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ap</span><span class="o">.</span><span class="n">network_wrappers</span><span class="p">[</span><span class="s1">&#39;main&#39;</span><span class="p">]</span><span class="o">.</span><span class="n">input_embedders_parameters</span><span class="o">.</span><span class="n">keys</span><span class="p">()</span>