Saved in:
Bibliographic Details
Main Authors: Ma, Xiaoteng, Chen, Junyao, Xia, Li, Yang, Jun, Zhao, Qianchuan, Zhou, Zhengyuan
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2004.14547
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We present Distributional Soft Actor-Critic (DSAC), a distributional reinforcement learning (RL) algorithm that combines the strengths of distributional information of accumulated rewards and entropy-driven exploration from Soft Actor-Critic (SAC) algorithm. DSAC models the randomness in both action and rewards, surpassing baseline performances on various continuous control tasks. Unlike standard approaches that solely maximize expected rewards, we propose a unified framework for risk-sensitive learning, one that optimizes the risk-related objective while balancing entropy to encourage exploration. Extensive experiments demonstrate DSAC's effectiveness in enhancing agent performances for both risk-neutral and risk-sensitive control tasks.