首页|SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

Mingzhong Wang Xin Li Hongyu Zang

来源：

Arxiv

SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

Mingzhong Wang Xin Li Hongyu Zang

作者信息

Abstract

This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods. Addressing the computational complexity, stringent assumptions and representation collapse challenges in existing work of bisimulation metric, we devise Simple State Representation (SimSR) operator. SimSR enables us to design a stochastic approximation method that can practically learn the mapping functions (encoders) from observations to latent representation space. In addition to the theoretical analysis and comparison with the existing work, we experimented and compared our work with recent state-of-the-art solutions in visual MuJoCo tasks. The results shows that our model generally achieves better performance and has better robustness and good generalization.

引用本文复制引用

Mingzhong Wang,Xin Li,Hongyu Zang.SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning[EB/OL].(2021-12-30)[2026-04-04].https://arxiv.org/abs/2112.15303.

学科分类

计算技术、计算机技术

首发时间： 2021-12-30

下载量：0

点击量：3

段落导航

SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

SimSR: Simple Distance-based State Representation for Deep Reinforcement Learning

Abstract

引用本文复制引用

学科分类

评论