This repository contains the DSAC algorithm using pytorch, see details in our paper
- Jingliang Duan, Ynag Guan, Shengbo Eben Li, et al. Distributional Soft Actor-critic: Off-policy Reinforcement Learning for Addressing Value Estimation Errors. IEEE Transactions on Neural Networks and Learning Systems, 2021.
- Preprint Materials: https://arxiv.org/abs/2001.02811
- Video: https://youtu.be/TTmYAup79N0 ; https://www.bilibili.com/video/BV1fa4y1h7Mo
Our scripts work for Ubuntu, Windows, and MacOS.