Factored Adaptation for Non-Stationary Reinforcement Learning
Feng, Fan, Huang, Biwei, Zhang, Kun, Magliacane, Sara
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-17-2022
- Country:
- Asia
- China > Hong Kong (0.04)
- Middle East > Jordan (0.04)
- Europe
- Netherlands > North Holland
- Amsterdam (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Netherlands > North Holland
- North America > United States
- California > Alameda County
- Berkeley (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- California > Alameda County
- Asia
- Genre:
- Research Report > New Finding (0.87)
- Industry:
- Health & Medicine (0.46)
- Information Technology (0.67)
- Technology: