stable-baselines3/README.md

<img src="docs/\_static/img/logo.png" align="right" width="40%"/>

[![Build Status](https://travis-ci.com/hill-a/stable-baselines.svg?branch=master)](https://travis-ci.com/hill-a/stable-baselines) [![Documentation Status](https://readthedocs.org/projects/stable-baselines/badge/?version=master)](https://stable-baselines.readthedocs.io/en/master/?badge=master)

# Torchy Baselines

PyTorch version of [Stable Baselines](https://github.com/hill-a/stable-baselines), a set of improved implementations of reinforcement learning algorithms.

## Implemented Algorithms

- A2C
- CEM-RL (with TD3)
- PPO
- SAC
- TD3


## Roadmap

TODO:
- save/load
- better predict
- complete logger
- SDE: learn the feature extractor?
- Refactor: buffer with numpy array instead of pytorch
- Refactor: remove duplicated code for evaluation
- plotting? -> zoo

Later:
- get_parameters / set_parameters
- CNN policies + normalization
- tensorboard support
- DQN
- TRPO
- ACER
- DDPG
- HER -> use stable-baselines because does not depends on tf?
Add logo 2019-09-22 11:57:18 +00:00			`<img src="docs/\_static/img/logo.png" align="right" width="40%"/>`

			`[![Build Status](https://travis-ci.com/hill-a/stable-baselines.svg?branch=master)](https://travis-ci.com/hill-a/stable-baselines) [![Documentation Status](https://readthedocs.org/projects/stable-baselines/badge/?version=master)](https://stable-baselines.readthedocs.io/en/master/?badge=master)`

			`# Torchy Baselines`

			`PyTorch version of [Stable Baselines](https://github.com/hill-a/stable-baselines), a set of improved implementations of reinforcement learning algorithms.`
Add roadmap 2019-09-22 11:43:01 +00:00
Add a parameter to disable ortho init 2019-09-26 14:29:47 +00:00			`## Implemented Algorithms`

Add A2C 2019-10-25 08:59:15 +00:00			`- A2C`
Add a parameter to disable ortho init 2019-09-26 14:29:47 +00:00			`- CEM-RL (with TD3)`
			`- PPO`
			`- SAC`
			`- TD3`


			`## Roadmap`

Add roadmap 2019-09-22 11:43:01 +00:00			`TODO:`
			`- save/load`
Add A2C 2019-10-25 08:59:15 +00:00			`- better predict`
			`- complete logger`
Solve NaN issue and reduce number of parameters 2019-11-13 12:02:37 +00:00			`- SDE: learn the feature extractor?`
Cleanup + update doc 2019-11-22 12:33:12 +00:00			`- Refactor: buffer with numpy array instead of pytorch`
			`- Refactor: remove duplicated code for evaluation`
			`- plotting? -> zoo`
Add roadmap 2019-09-22 11:43:01 +00:00
			`Later:`
			`- get_parameters / set_parameters`
			`- CNN policies + normalization`
			`- tensorboard support`
			`- DQN`
			`- TRPO`
			`- ACER`
Add a parameter to disable ortho init 2019-09-26 14:29:47 +00:00			`- DDPG`
Add roadmap 2019-09-22 11:43:01 +00:00			`- HER -> use stable-baselines because does not depends on tf?`