learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-08-14 17:41:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

dqn experiment link

Browse Source
This commit is contained in:
Varuna Jayasiri
2021-10-02 19:01:32 +05:30
parent 06a79203e5
commit dc13d22873
10 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/rl/dqn/experiment.html
View File

@ -71,7 +71,7 @@
<p>This experiment trains a Deep Q Network (DQN) to play Atari Breakout game on OpenAI Gym.
It runs the <a href="../game.html">game environments on multiple processes</a> to sample efficiently.</p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
<a href="https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
<a href="https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">16</span><span></span><span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span>
@ -986,7 +986,7 @@ Gradients shouldn&rsquo;t propagate for these</p>
<p>Learning rate.</p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">274</span> <span class="s1">&#39;learning_rate&#39;</span><span class="p">:</span> <span class="n">FloatDynamicHyperParam</span><span class="p">(</span><span class="mf">2.5e-4</span><span class="p">,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mf">1e-3</span><span class="p">)),</span>
<div class="highlight"><pre><span class="lineno">274</span> <span class="s1">&#39;learning_rate&#39;</span><span class="p">:</span> <span class="n">FloatDynamicHyperParam</span><span class="p">(</span><span class="mf">1e-4</span><span class="p">,</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mf">1e-3</span><span class="p">)),</span>
<span class="lineno">275</span> <span class="p">}</span></pre></div>
</div>
</div>

2
docs/rl/dqn/index.html
View File

@ -74,7 +74,7 @@
and Double Q Network.</p>
<p>Here is the <a href="experiment.html">experiment</a> and <a href="model.html">model</a> implementation.</p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
<a href="https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
<a href="https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">25</span><span></span><span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>

2
docs/rl/dqn/model.html
View File

@ -69,7 +69,7 @@
</div>
<h1>Deep Q Network (DQN) Model</h1>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
<a href="https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
<a href="https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">13</span><span></span><span class="kn">import</span> <span class="nn">torch</span>

2
docs/rl/dqn/replay_buffer.html
View File

@ -71,7 +71,7 @@
<p>This implements paper <a href="https://papers.labml.ai/paper/1511.05952">Prioritized experience replay</a>,
using a binary segment tree.</p>
<p><a href="https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb"><img alt="Open In Colab" src="https://colab.research.google.com/assets/colab-badge.svg" /></a>
<a href="https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
<a href="https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710"><img alt="View Run" src="https://img.shields.io/badge/labml-experiment-brightgreen" /></a></p>
</div>
<div class='code'>
<div class="highlight"><pre><span class="lineno">16</span><span></span><span class="kn">import</span> <span class="nn">random</span>

6
docs/sitemap.xml
View File

@ -876,14 +876,14 @@
<url>
<loc>https://nn.labml.ai/rl/dqn/index.html</loc>
<lastmod>2021-08-19T16:30:00+00:00</lastmod>
<lastmod>2021-10-02T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>
<url>
<loc>https://nn.labml.ai/rl/dqn/model.html</loc>
<lastmod>2021-08-19T16:30:00+00:00</lastmod>
<lastmod>2021-10-02T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>
@ -897,7 +897,7 @@
<url>
<loc>https://nn.labml.ai/rl/dqn/replay_buffer.html</loc>
<lastmod>2021-08-17T16:30:00+00:00</lastmod>
<lastmod>2021-10-02T16:30:00+00:00</lastmod>
<priority>1.00</priority>
</url>

2
labml_nn/rl/dqn/__init__.py
View File

@ -19,7 +19,7 @@ This is a [PyTorch](https://pytorch.org) implementation of paper
Here is the [experiment](experiment.html) and [model](model.html) implementation.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710)
"""
from typing import Tuple

2
labml_nn/rl/dqn/experiment.ipynb
View File

@ -146,7 +146,7 @@
" # Target model updating interval\n",
" 'update_target_model': 250,\n",
" # Learning rate.\n",
" 'learning_rate': FloatDynamicHyperParam(2.5e-4, (0, 1e-3)),\n",
" 'learning_rate': FloatDynamicHyperParam(1e-4, (0, 1e-3)),\n",
"}"
]
},

2
labml_nn/rl/dqn/experiment.py
View File

@ -10,7 +10,7 @@ This experiment trains a Deep Q Network (DQN) to play Atari Breakout game on Ope
It runs the [game environments on multiple processes](../game.html) to sample efficiently.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710)
"""
import numpy as np

2
labml_nn/rl/dqn/model.py
View File

@ -7,7 +7,7 @@ summary: Implementation of neural network model for Deep Q Network (DQN).
# Deep Q Network (DQN) Model
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710)
"""
import torch

2
labml_nn/rl/dqn/replay_buffer.py
View File

@ -10,7 +10,7 @@ This implements paper [Prioritized experience replay](https://papers.labml.ai/pa
using a binary segment tree.
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/labmlai/annotated_deep_learning_paper_implementations/blob/master/labml_nn/rl/dqn/experiment.ipynb)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/a0da8048235511ecb9affd797fa27714)
[![View Run](https://img.shields.io/badge/labml-experiment-brightgreen)](https://app.labml.ai/run/fe1ad986237511ec86e8b763a2d3f710)
"""
import random