A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces

Abstract

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.

Update following the publication in AISTATS 2021. Fixed typos and lemma about runtime

References in corpus (6)

• Weighted Linear Bandits for Non-Stationary Environments
• Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
• A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free
• Variational Regret Bounds for Reinforcement Learning
• Efficient Model-free Reinforcement Learning in Metric Spaces
• Adaptive Discretization for Model-Based Reinforcement Learning

Cited by in corpus (4)

• Corruption-robust exploration in episodic reinforcement learning
• Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach
• Robust Policy Gradient against Strong Data Corruption
• Efficient Learning in Non-Stationary Linear Markov Decision Processes