Timezone: »

 
Short Talk 3 - A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces
Omar Darwiche Domingues

Fri Jul 17 11:50 AM -- 12:05 PM (PDT) @

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.

Omar Darwiche Domingues, Pierre MENARD, Matteo Pirotta, Emilie Kaufmann, Michal Valko

Author Information

Omar Darwiche Domingues (Inria)

More from the Same Authors