Reinforcement-learning-with-tensorflow - GitLite

KO | EN

gitlite — search

#javascript #hacktoberfest #ai #typescript #llm #go #rust #docker #nodejs #java #windows #cli #security #ios

Reinforcement-learning-with-tensorflow

(★ 9,503)

Simple Reinforcement learning tutorials, 莫烦Python 中文AI教学

파일 탐색기

최종 버전 다운로드 (.zip)

- - A3C_continuous_action.py
  - A3C_discrete_action.py
  - A3C_distributed_tf.py
  - A3C_RNN.py
- - maze_env.py
  - RL_brain.py
  - run_this.py
- - discrete_DPPO.py
  - DPPO.py
  - simply_PPO.py
- - treasure_on_right.py
- - maze_env.py
  - RL_brain.py
  - run_this.py
- - maze_env.py
  - RL_brain.py
  - run_this.py
- - maze_env.py
  - RL_brain.py
  - run_this.py
- - RL_brain.py
  - run_Pendulum.py
- - RL_brain.py
  - run_MountainCar.py
- - RL_brain.py
  - run_Pendulum.py
- - DQN_modified.py
  - maze_env.py
  - RL_brain.py
  - run_this.py
- - RL_brain.py
  - run_CartPole.py
  - run_MountainCar.py
- - RL_brain.py
  - run_CartPole.py
  - run_MountainCar.py
- - AC_CartPole.py
  - AC_continue_Pendulum.py
- - DDPG.py
  - DDPG_update.py
  - DDPG_update2.py
- - Curiosity.png
  - Curiosity.py
  - Random_Network_Distillation.py
- - car_env.py
  - collision.py
  - DDPG.py
- - A3C.py
  - arm_env.py
  - DDPG.py
  - DPPO.py
- - A3C.py
  - A3C_rnn.py
  - DDPG.py
- - A3C.py
  - DuelingDQNPrioritizedReplay.py
  - run_LunarLander.py
.gitignore
LICENCE
README.md
RL_cover.jpg

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

<p align="center">
    <a href="https://www.youtube.com/watch?v=pieI7rOXELI&list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba" target="_blank">
    <img width="60%" src="https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/blob/master/RL_cover.jpg" style="max-width:100%;">
    </a>
</p>

<br>

# Reinforcement Learning Methods and Tutorials

In these tutorials for reinforcement learning, it covers from the basic RL algorithms to advanced algorithms developed recent years.

**If you speak Chinese, visit [莫烦 Python](https://mofanpy.com) or my [Youtube channel](https://www.youtube.com/channel/UCdyjiB5H8Pu7aDTNVXTTpcg) for more.**

**As many requests about making these tutorials available in English, please find them in this playlist:** ([https://www.youtube.com/playlist?list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba](https://www.youtube.com/playlist?list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba))

# Table of Contents

* Tutorials
    * [Simple entry example](contents/1_command_line_reinforcement_learning)
    * [Q-learning](contents/2_Q_Learning_maze)
    * [Sarsa](contents/3_Sarsa_maze)
    * [Sarsa(lambda)](contents/4_Sarsa_lambda_maze)
    * [Deep Q Network (DQN)](contents/5_Deep_Q_Network)
    * [Using OpenAI Gym](contents/6_OpenAI_gym)
    * [Double DQN](contents/5.1_Double_DQN)
    * [DQN with Prioitized Experience Replay](contents/5.2_Prioritized_Replay_DQN)
    * [Dueling DQN](contents/5.3_Dueling_DQN)
    * [Policy Gradients](contents/7_Policy_gradient_softmax)
    * [Actor-Critic](contents/8_Actor_Critic_Advantage)
    * [Deep Deterministic Policy Gradient (DDPG)](contents/9_Deep_Deterministic_Policy_Gradient_DDPG)
    * [A3C](contents/10_A3C)
    * [Dyna-Q](contents/11_Dyna_Q)
    * [Proximal Policy Optimization (PPO)](contents/12_Proximal_Policy_Optimization)
    * [Curiosity Model](/contents/Curiosity_Model), [Random Network Distillation (RND)](/contents/Curiosity_Model/Random_Network_Distillation.py)
* [Some of my experiments](experiments)
    * [2D Car](experiments/2D_car)
    * [Robot arm](experiments/Robot_arm)
    * [BipedalWalker](experiments/Solve_BipedalWalker)
    * [LunarLander](experiments/Solve_LunarLander)

# Some RL Networks
### [Deep Q Network](contents/5_Deep_Q_Network)

<a href="contents/5_Deep_Q_Network">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/4-3-2.png">
</a>

### [Double DQN](contents/5.1_Double_DQN)

<a href="contents/5.1_Double_DQN">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/4-5-3.png">
</a>

### [Dueling DQN](contents/5.3_Dueling_DQN)

<a href="contents/5.3_Dueling_DQN">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/4-7-4.png">
</a>

### [Actor Critic](contents/8_Actor_Critic_Advantage)

<a href="contents/8_Actor_Critic_Advantage">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/6-1-1.png">
</a>

### [Deep Deterministic Policy Gradient](contents/9_Deep_Deterministic_Policy_Gradient_DDPG)

<a href="contents/9_Deep_Deterministic_Policy_Gradient_DDPG">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/6-2-2.png">
</a>

### [A3C](contents/10_A3C)

<a href="contents/10_A3C">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/6-3-2.png">
</a>

### [Proximal Policy Optimization (PPO)](contents/12_Proximal_Policy_Optimization)

<a href="contents/12_Proximal_Policy_Optimization">
    <img class="course-image" src="https://mofanpy.com/static/results/reinforcement-learning/6-4-3.png">
</a>

### [Curiosity Model](/contents/Curiosity_Model)

<a href="/contents/Curiosity_Model">
    <img class="course-image" src="/contents/Curiosity_Model/Curiosity.png">
</a>

# Donation

*If this does help you, please consider donating to support me for better tutorials. Any contribution is greatly appreciated!*

<div >
  <a href="https://www.paypal.com/cgi-bin/webscr?cmd=_donations&amp;business=morvanzhou%40gmail%2ecom&amp;lc=C2&amp;item_name=MorvanPython&amp;currency_code=AUD&amp;bn=PP%2dDonationsBF%3abtn_donateCC_LG%2egif%3aNonHosted">
    <img style="border-radius: 20px;  box-shadow: 0px 0px 10px 1px  #888888;"
         src="https://www.paypalobjects.com/webstatic/en_US/i/btn/png/silver-pill-paypal-44px.png"
         alt="Paypal"
         height="auto" ></a>
</div>

<div>
  <a href="https://www.patreon.com/morvan">
    <img src="https://mofanpy.com/static/img/support/patreon.jpg"
         alt="Patreon"
         height=120></a>
</div>