https://github.com/pythonlessons/reinforcement_learning

Reinforcement learning tutorials
https://github.com/pythonlessons/reinforcement_learning

a2c a3c actor-critic-algorythm bipedalwalker d3qn ddqn dqn dueling-dqn lunarlander policy-gradient ppo ppo-agent reinforcement-learning

Last synced: 7 days ago
JSON representation

Reinforcement learning tutorials

• Host: GitHub
• URL: https://github.com/pythonlessons/reinforcement_learning
• Owner: pythonlessons
• License: mit
• Created: 2020-01-13T14:27:41.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-25T01:33:39.000Z (over 1 year ago)
• Last Synced: 2024-12-07T02:33:47.150Z (15 days ago)
• Topics: a2c, a3c, actor-critic-algorythm, bipedalwalker, d3qn, ddqn, dqn, dueling-dqn, lunarlander, policy-gradient, ppo, ppo-agent, reinforcement-learning
• Language: Python
• Homepage: https://pylessons.com/
• Size: 87 MB
• Stars: 362
• Watchers: 7
• Forks: 154
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Reinforcement Learning Tutorials:

*2020-10-07 added support for Tensorflow 2.3.1*

PPO and PPO_CNN agents playing Pong-v0 game:


![PPO agent](11_Pong-v0_PPO/gameplay.gif)

![PPO CNN agent](11_Pong-v0_PPO/gameplay_CNN.gif)

*2020-10-10 added LunarLander-v2_PPO Continuous code for Tensorflow 2.3.1*:

![LunarLander-v2_PPO](https://github.com/pythonlessons/Reinforcement_Learning/blob/master/LunarLander-v2_PPO/gameplay.gif)

*2020-10-23 added BipedalWalker-v3_PPO code for Tensorflow 2.3.1*:

![BipedalWalker-v3_PPO_PPO](https://github.com/pythonlessons/Reinforcement_Learning/blob/master/BipedalWalker-v3_PPO/gameplay.gif)

1. [Deep Q Learning tutorial (DQN)](https://pylessons.com/CartPole-reinforcement-learning/)

2. [Double Deep Q Learning tutorial (DDQN)](https://pylessons.com/CartPole-DDQN/)

3. [Dueling Double Deep Q Learning tutorial (D3QN)](https://pylessons.com/CartPole-DDDQN/)

4. [Epsilon Greedy Dueling Double Deep Q Learning tutorial (D3QN)](https://pylessons.com/Epsilon-Greedy-DQN/)

5. [Prioritized Experience Replay (PER) D3QN tutorial](https://pylessons.com/CartPole-PER/)

6. [D3QN PER with Convolutional Neural Networks tutorial](https://pylessons.com/CartPole-PER-CNN/)

7. [A.I. learns to play Pong with DQN](https://pylessons.com/DQN-PONG/)

8. [Introduction to RL Policy Gradient (PG or REINFORCE)](https://pylessons.com/Beyond-DQN/)

9. [Introduction to RL Advanced Actor Critic algorythm (A2C)](https://pylessons.com/A2C-reinforcement-learning/)

10. [Introduction to RL Asynchronous Advanced Actor Critic algorythm (A3C)](https://pylessons.com/A3C-reinforcement-learning/)

11. [Introduction to RL Proximal Policy Optimization algorythm (PPO)](https://pylessons.com/PPO-reinforcement-learning/)

12. [Let’s code from scratch a discrete Reinforcement Learning rocket landing agent! (PPO)](https://pylessons.com/LunarLander-v2-PPO/)

13. [Continuous Proximal Policy Optimization Tutorial with OpenAI gym environment! (PPO)](https://pylessons.com/BipedalWalker-v3-PPO/)





PPO Pong-v0 Learning curve: