Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Roy, Srinjoy, Das, Swagatam
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913296531062784
author Roy, Srinjoy
Das, Swagatam
author_facet Roy, Srinjoy
Das, Swagatam
contents Accounting for the uncertainty of value functions boosts exploration in Reinforcement Learning (RL). Our work introduces Maximum Mean Discrepancy Q-Learning (MMD-QL) to improve Wasserstein Q-Learning (WQL) for uncertainty propagation during Temporal Difference (TD) updates. MMD-QL uses the MMD barycenter for this purpose, as MMD provides a tighter estimate of closeness between probability measures than the Wasserstein distance. Firstly, we establish that MMD-QL is Probably Approximately Correct in MDP (PAC-MDP) under the average loss metric. Concerning the accumulated rewards, experiments on tabular environments show that MMD-QL outperforms WQL and other algorithms. Secondly, we incorporate deep networks into MMD-QL to create MMD Q-Network (MMD-QN). Making reasonable assumptions, we analyze the convergence rates of MMD-QN using function approximation. Empirical results on challenging Atari games demonstrate that MMD-QN performs well compared to benchmark deep RL algorithms, highlighting its effectiveness in handling large state-action spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00686
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning
Roy, Srinjoy
Das, Swagatam
Machine Learning
Accounting for the uncertainty of value functions boosts exploration in Reinforcement Learning (RL). Our work introduces Maximum Mean Discrepancy Q-Learning (MMD-QL) to improve Wasserstein Q-Learning (WQL) for uncertainty propagation during Temporal Difference (TD) updates. MMD-QL uses the MMD barycenter for this purpose, as MMD provides a tighter estimate of closeness between probability measures than the Wasserstein distance. Firstly, we establish that MMD-QL is Probably Approximately Correct in MDP (PAC-MDP) under the average loss metric. Concerning the accumulated rewards, experiments on tabular environments show that MMD-QL outperforms WQL and other algorithms. Secondly, we incorporate deep networks into MMD-QL to create MMD Q-Network (MMD-QN). Making reasonable assumptions, we analyze the convergence rates of MMD-QN using function approximation. Empirical results on challenging Atari games demonstrate that MMD-QN performs well compared to benchmark deep RL algorithms, highlighting its effectiveness in handling large state-action spaces.
title Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2404.00686