https://github.com/agentmaker/paddle-rlbooks

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.
https://github.com/agentmaker/paddle-rlbooks

actor-critic c51 ddpg double-dqn dqn dueling-dqn noisy-dqn nstep-dqn paddlepaddle policy-gradient policy-gradient-with-baseline policy-iteration q-learning reinforce reinforcement-learning sac sarsa td3 value-iteration

Last synced: 9 months ago
JSON representation

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.

• Host: GitHub
• URL: https://github.com/agentmaker/paddle-rlbooks
• Owner: AgentMaker
• License: apache-2.0
• Created: 2021-03-21T06:57:18.000Z (about 5 years ago)
• Default Branch: main
• Last Pushed: 2021-11-13T05:15:20.000Z (over 4 years ago)
• Last Synced: 2025-04-02T03:01:43.460Z (about 1 year ago)
• Topics: actor-critic, c51, ddpg, double-dqn, dqn, dueling-dqn, noisy-dqn, nstep-dqn, paddlepaddle, policy-gradient, policy-gradient-with-baseline, policy-iteration, q-learning, reinforce, reinforcement-learning, sac, sarsa, td3, value-iteration
• Language: Python
• Homepage:
• Size: 14.1 MB
• Stars: 110
• Watchers: 3
• Forks: 13
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Paddle-RLBooks

Welcome to Paddle-RLBooks which is a reinforcement learning code study guide based on pure PaddlePaddle.

欢迎来到Paddle-RLBooks，该仓库主要是针对强化学习中的一些算法进行整理，包括DQN、TD3、SAC等算法，并且每个都配备了游戏可直接一键运行，欢迎star~

## Show

![](./material/flappybird.jpg)

## Codes

- Release

  - [x] [Policy Iteration](./policy_iteration)

  - [x] [Value Iteration](./value_iteration)

  - [x] [Sarsa](./sarsa)

  - [x] [Q-learning](./qlearning)

  - [x] [DQN](./dqn)

    - [x] [DQN](./dqn/dqn)

    - [x] [Nstep-DQN](./dqn/nstep_dqn)

    - [x] [Double-DQN](./dqn/double_dqn)

    - [x] [Dueling-DQN](./dqn/dueling_dqn)

    - [x] [Noisy-DQN](./dqn/dqn_noisy_networks)

    - [x] [C51](./dqn/categorical_dqn(C51))

  - [x] [Policy Gradient](./policy_gradient)

    - [x] [Policy Gradient Basic](./policy_gradient)

    - [x] [Reinforce](./policy_gradient)

    - [x] [Policy Gradient With Baseline](./policy_gradient)

  - [x] [Actor-Critic](./actor_critic)

  - [x] [DDPG](./ddpg)

  - [x] [TD3](./td3)

  - [x] [SAC](./sac)

- Coming Soon

  - [ ] TRPO

  - [ ] ACKTR

  - [ ] A2C

  - [ ] A3C

  - [ ] PPO

  - [ ] DRQN

  - [ ] QMIX

  - [ ] MAPPDG

  - [ ] MFMARL

## Contact us

Email : [agentmaker@163.com]()


QQ Group : 1005109853