uotter / VEM

Codes accompanying the paper "Offline Reinforcement Learning with Value-Based Episodic Memory" (ICLR 2022 https://arxiv.org/abs/2110.09796)

Value-Based Episodic Memory Control

This is a pytorch implementation of VEM on Datasets for Deep Data-Driven Reinforcement Learning (D4RL), the corresponding paper of VEM is Offline Reinforcement Learning with Value-Based Episodic Memory.

Requirements

• python=3.6.5
• Datasets for Deep Data-Driven Reinforcement Learning (D4RL)
• torch=1.1.0

Quick Start

$ python3 main.py

Citing

If you find this open source release useful, please reference in your paper:

@article{ma2021offline,
  title={Offline Reinforcement Learning with Value-based Episodic Memory},
  author={Ma, Xiaoteng and Yang, Yiqin and Hu, Hao and Liu, Qihan and Yang, Jun and Zhang, Chongjie and Zhao, Qianchuan and Liang, Bin},
  journal={arXiv preprint arXiv:2110.09796},
  year={2021}
}

Note

• If you have any questions, please contact me: [e-mail].