Skip to main content
Article
Factored Adaptation for Non-stationary Reinforcement Learning
Advances in Neural Information Processing Systems
  • Fan Feng, City University of Hong Kong
  • Biwei Huang, Carnegie Mellon University
  • Kun Zhang, Carnegie Mellon University & Mohamed bin Zayed University of Artificial Intelligence
  • Sara Magliacane, Universiteit van Amsterdam
Document Type
Conference Proceeding
Abstract

Dealing with non-stationarity in environments (e.g., in the transition dynamics) and objectives (e.g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL). While most current approaches model the changes as a single shared embedding vector, we leverage insights from the recent causality literature to model non-stationarity in terms of individual latent change factors, and causal graphs across different environments. In particular, we propose Factored Adaptation for Non-Stationary RL (FANS-RL), a factored adaption approach that learns jointly both the causal structure in terms of a factored MDP, and a factored representation of the individual time-varying change factors. We prove that under standard assumptions, we can completely recover the causal graph representing the factored transition and reward function, as well as a partial structure between the individual change factors and the state components. Through our general framework, we can consider general non-stationary scenarios with different function types and changing frequency, including changes across episodes and within episodes. Experimental results demonstrate that FANS-RL outperforms existing approaches in terms of return, compactness of the latent state representation, and robustness to varying degrees of non-stationarity.

Publication Date
12-1-2022
Keywords
  • Structure (composition)
Comments

Access available at NeurIPS Proceedings

Citation Information
F. Feng, et al, "Factored Adaptation for Non-Stationary Reinforcement Learning", in 36th Conference on Neural Information Processing Systems (NeurIPS 2022), Advances in Neural Info. Processing Systems, Dec 2022. [Online] Available: https://proceedings.neurips.cc/paper_files/paper/2022/file/cf4356f994917177213c55ff438ddf71-Paper-Conference.pdf