https://github.com/threewisemonkeys-as/myrl

Implementations of some standard reinforcement learning algorithms
https://github.com/threewisemonkeys-as/myrl

Last synced: 2 months ago
JSON representation

Implementations of some standard reinforcement learning algorithms

• Host: GitHub
• URL: https://github.com/threewisemonkeys-as/myrl
• Owner: threewisemonkeys-as
• License: mit
• Created: 2020-06-08T18:01:20.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2020-08-07T04:12:26.000Z (almost 5 years ago)
• Last Synced: 2025-02-09T20:43:32.397Z (4 months ago)
• Language: Python
• Size: 639 KB
• Stars: 1
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# myrl

Implementations of some standard reinforcement learning algorithms

- Written in pytorch

- All implentations are encapsulated into a single file

- Algorithms implemted as classes which take OpenAI gym env as inputs

- All classes have uniform interface with `train` and `eval` methods

- All references are given in the code

Algorithms -

- [X] Vanilla Policy Gradient (VPG)

- [X] Deep Q Network (DQN)

- [X] Deep Deterministic Policy Gradient (DDPG)

- [X] Twin Delayed DDPG (TD3)

- [X] Soft Actor Critic

- [X] Proximal Policy Optimization

- [ ] Trust Region Policy Optimization

Features to add -

- [ ] Better hyperparamter management

- [ ] Adding tensorboard logging

- [ ] Add documentation for each algorithm

- [ ] Add results for each algorithm