https://github.com/wondervictor/reinforcement.learning
Reinforcement Learning Playground
https://github.com/wondervictor/reinforcement.learning
a2c ddpg deep-reinforcement-learning dqn dueling-network-architecture reinforcement-learning
Last synced: 7 months ago
JSON representation
Reinforcement Learning Playground
- Host: GitHub
- URL: https://github.com/wondervictor/reinforcement.learning
- Owner: wondervictor
- Created: 2018-01-25T08:48:55.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-03-02T12:34:13.000Z (over 7 years ago)
- Last Synced: 2025-01-17T08:35:58.844Z (9 months ago)
- Topics: a2c, ddpg, deep-reinforcement-learning, dqn, dueling-network-architecture, reinforcement-learning
- Language: Python
- Size: 526 KB
- Stars: 1
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Reinforcement.Learning
**Contributions are welcome**
### Progress
1. - [x] Deep Q Network
2. - [x] Dueling Q Network
3. - [x] Policy Gradient: **REINFORCE**
4. - [x] Advantage Actor-Critic
5. - [x] Deep Deterministic Policy Gradient
### TODO
1. - [ ] Asynchronous Advantage Actor-Critic (A3C)
2. - [ ] Estimate the concrete performance of each algorithms
### Licence
**MIT Licence**