vix.ing · top · new · best · stats · spec

Transition Transfer Q-Learning for Composite Markov Decision Processes

2025/02/01 by Chai, Jinhang, Elynn Chen, Lin F. Yang +2 · 1 citation
Computer Science · Engineering · #Anomaly Detection Techniques and Applications #Data Stream Mining Techniques #FOS: Computer and information sciences #Fault Detection and Control Systems #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2502.00534

openalex publication_date 2025/02/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

To bridge the gap between empirical success and theoretical understanding in transfer reinforcement learning (RL), we study a principled approach with provable performance guarantees. We introduce a novel composite MDP framework where high-dimensional transition dynamics are modeled as the sum of a low-rank component representing shared structure and a sparse component capturing task-specific variations. This relaxes the common assumption of purely low-rank transition models, allowing for more realistic scenarios where tasks share core dynamics but maintain individual variations. We introduce UCB-TQL (Upper Confidence Bound Transfer Q-Learning), designed for transfer RL scenarios where multiple tasks share core linear MDP dynamics but diverge along sparse dimensions. When applying UCB-TQL to a target task after training on a source task with sufficient trajectories, we achieve a regret bound of O(√(eH5N)) that scales independently of the ambient dimension. Here, N represents the number of trajectories in the target task, while e quantifies the sparse differences between tasks. This result demonstrates substantial improvement over single task RL by effectively leveraging their structural similarities. Our theoretical analysis provides rigorous guarantees for how UCB-TQL simultaneously exploits shared dynamics while adapting to task-specific variations.

Cited by

Related