mirror of
https://github.com/labmlai/annotated_deep_learning_paper_implementations.git
synced 2025-08-26 08:41:23 +08:00
ppo
This commit is contained in:
@ -86,7 +86,7 @@ It runs the <a href="../game.html">game environments on multiple processes</a> t
|
||||
<span class="lineno">19</span><span class="kn">from</span> <span class="nn">torch.distributions</span> <span class="kn">import</span> <span class="n">Categorical</span>
|
||||
<span class="lineno">20</span>
|
||||
<span class="lineno">21</span><span class="kn">from</span> <span class="nn">labml</span> <span class="kn">import</span> <span class="n">monit</span><span class="p">,</span> <span class="n">tracker</span><span class="p">,</span> <span class="n">logger</span><span class="p">,</span> <span class="n">experiment</span>
|
||||
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml.internal.configs.dynamic_hyperparam</span> <span class="kn">import</span> <span class="n">FloatDynamicHyperParam</span>
|
||||
<span class="lineno">22</span><span class="kn">from</span> <span class="nn">labml.configs</span> <span class="kn">import</span> <span class="n">FloatDynamicHyperParam</span>
|
||||
<span class="lineno">23</span><span class="kn">from</span> <span class="nn">labml_helpers.module</span> <span class="kn">import</span> <span class="n">Module</span>
|
||||
<span class="lineno">24</span><span class="kn">from</span> <span class="nn">labml_nn.rl.game</span> <span class="kn">import</span> <span class="n">Worker</span>
|
||||
<span class="lineno">25</span><span class="kn">from</span> <span class="nn">labml_nn.rl.ppo</span> <span class="kn">import</span> <span class="n">ClippedPPOLoss</span><span class="p">,</span> <span class="n">ClippedValueFunctionLoss</span>
|
||||
|
@ -701,7 +701,7 @@
|
||||
|
||||
<url>
|
||||
<loc>https://nn.labml.ai/rl/ppo/index.html</loc>
|
||||
<lastmod>2021-03-05T16:30:00+00:00</lastmod>
|
||||
<lastmod>2021-03-27T16:30:00+00:00</lastmod>
|
||||
<priority>1.00</priority>
|
||||
</url>
|
||||
|
||||
@ -715,7 +715,7 @@
|
||||
|
||||
<url>
|
||||
<loc>https://nn.labml.ai/rl/ppo/readme.html</loc>
|
||||
<lastmod>2021-02-23T16:30:00+00:00</lastmod>
|
||||
<lastmod>2021-03-27T16:30:00+00:00</lastmod>
|
||||
<priority>1.00</priority>
|
||||
</url>
|
||||
|
||||
|
Reference in New Issue
Block a user