Deep Reinforcement Learning amidst Lifelong Non-Stationarity

TL;DR

This paper introduces a novel off-policy reinforcement learning algorithm designed to handle lifelong non-stationarity by learning environment representations from past experiences, outperforming existing methods in dynamic settings.

Contribution

The authors formalize lifelong non-stationarity in RL and develop a latent variable-based off-policy algorithm that adapts to persistent environment changes.

Findings

Our method significantly outperforms non-adaptive approaches in non-stationary environments.

The approach effectively learns environment representations that capture ongoing changes.

Empirical results demonstrate robustness to continuous environment shifts.

Abstract

As humans, our goals and our environment are persistently changing throughout our lifetime based on our experiences, actions, and internal and external drives. In contrast, typical reinforcement learning problem set-ups consider decision processes that are stationary across episodes. Can we develop reinforcement learning algorithms that can cope with the persistent change in the former, more realistic problem settings? While on-policy algorithms such as policy gradients in principle can be extended to non-stationary settings, the same cannot be said for more efficient off-policy algorithms that replay past experiences when learning. In this work, we formalize this problem setting, and draw upon ideas from the online learning and probabilistic inference literature to derive an off-policy RL algorithm that can reason about and tackle such lifelong non-stationarity. Our method leverages latent variable models to learn a representation of the environment from current and past experiences, and performs off-policy RL with this representation. We further introduce several simulation environments that exhibit lifelong non-stationarity, and empirically find that our approach substantially outperforms approaches that do not reason about environment shift.