0

Soft Actor-Critic Algorithms and Applications

Soft Actor-Critic (SAC) is an off-policy actor-critic deep reinforcement learning algorithm that incorporates entropy maximization, hyperparameter tuning, and stability improvements, achieving state-of-the-art performance on various tasks.

Year
2018
Venue
arXiv 2018
Authors
11
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/1812.05905v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

Authors

11