Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach

Authors

  • Zhiyuan Yao Stevens Institute of Technology
  • Ionut Florescu Stevens Institute of Technology
  • Chihoon Lee Stevens Institute of Technology

DOI:

https://doi.org/10.1609/icaps.v34i1.31529

Abstract

In this paper we are introducing a new reinforcement learning method for control problems in environments with delayed feedback. Specifically, our method employs stochastic planning, versus previous methods that used deterministic planning. This allows us to embed risk preference in the policy optimization problem. We show that this formulation can recover the optimal policy for problems with deterministic transitions. We contrast our policy with two prior methods from literature. We apply the methodology to simple tasks to understand its features. Then, we compare the performance of the methods in controlling multiple Atari games.

Downloads

Published

2024-05-30

How to Cite

Yao, Z., Florescu, I., & Lee, C. (2024). Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach. Proceedings of the International Conference on Automated Planning and Scheduling, 34(1), 663-670. https://doi.org/10.1609/icaps.v34i1.31529