8000 GitHub - Sohojoe/baby_rl: Reinforcement Learning Algorithms in PyTorch
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Sohojoe/baby_rl

Repository files navigation

baby_rl

Reinforcement Learning Algorithms in PyTorch

Based on https://github.com/ShangtongZhang/DeepRL hash 5d0ad07

  • Use Marathon Envs instead of Majoco
  • removed dependency on OpenAI Baselines

Implemented algorithms:

  • Twined Delayed DDPG (TD3)

Dependency

  • PyTorch v1.4.0
  • Python 3.6, 3.5
  • Core dependencies: pip install -e .
  • Download MarathonEnvs binary
  • xxxxx show how ****

Install

conda env create -f environment.yml
conda activate baby_rl
# manually install marathon-envs
pip install -r requirements.txt
pip install -e .

for tensorboard

tensorboard --logdir=tf_log

Usage

examples.py contains examples for all the implemented algorithms

References

About

Reinforcement Learning Algorithms in PyTorch

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

0