takuya-ki / rl

Implementations of reinforcement learning

rl

Implementations of reinforcement learning examples

References

• PyTorch tutorial
• kuka-rl

Dependencies (tested)

• Windows 10
  • GPU: NVIDIA GeForce RTX 3080
    • Driver 471.11
    • CUDA 11.1
• Ubuntu 18.04
  • GPU: NVIDIA GeForce RTX 3080
    • Driver 470.57
    • CUDA 11.0
• Python 3.7.3
  • gym 0.20.0
  • numpy 1.21.5
  • ipython 7.31.1
  • pyglet 1.5.21
  • matplotlib 3.1.1
  • torch 1.9.1
  • torchvision 0.10.1
  • torchaudio 0.9.1
  • pybullet 3.2.0
  • tensorboardX 2.4.1

Installation

git clone [e-mail]:takuya-ki/rl.git; cd rl
pip install -r requirements.txt

Usage

python cartpole/cartpole_qrl.py
python cartpole/cartpole_dqrl.py

python robot/train_kuka_grasp.py
python robot/eval_kuka_grasp.py

Author / Contributor

Takuya Kiyokawa

LICENSE

This software is released under the MIT License, see LICENSE.
This software includes the work that is distributed in the Apache License 2.0.