SimSR: Simple Distance-Based State Representations for Deep Reinforcement Learning

Authors

  • Hongyu Zang Beijing Institute of Technology
  • Xin Li Beijing Institute of Technology
  • Mingzhong Wang The University of the Sunshine Coast

DOI:

https://doi.org/10.1609/aaai.v36i8.20883

Keywords:

Machine Learning (ML)

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.

Downloads

Published

2022-06-28

How to Cite

Zang, H., Li, X., & Wang, M. (2022). SimSR: Simple Distance-Based State Representations for Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8997-9005. https://doi.org/10.1609/aaai.v36i8.20883

Issue

Section

AAAI Technical Track on Machine Learning III