A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
This work addresses non-stationary RL for environments with metric structures, offering a generalization of existing methods, though it appears incremental in its approach.
The authors tackled the problem of episodic reinforcement learning in non-stationary Markov Decision Processes with metric state-action spaces by proposing KeRNS, a kernel-based algorithm, and proved a regret bound scaling with covering dimension and total variation, achieving competitive performance in experiments.
In this work, we propose KeRNS: an algorithm for episodic reinforcement learning in non-stationary Markov Decision Processes (MDPs) whose state-action set is endowed with a metric. Using a non-parametric model of the MDP built with time-dependent kernels, we prove a regret bound that scales with the covering dimension of the state-action space and the total variation of the MDP with time, which quantifies its level of non-stationarity. Our method generalizes previous approaches based on sliding windows and exponential discounting used to handle changing environments. We further propose a practical implementation of KeRNS, we analyze its regret and validate it experimentally.