Importance Weighted Transfer of Samples in Reinforcement Learning

Abstract

We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related approaches focus on selecting the most relevant source samples for solving the target task, but then all the transferred samples are used without considering anymore the discrepancies between the task models. In this paper, we propose a model-based technique that automatically estimates the relevance (importance weight) of each source sample for solving the target task. In the proposed approach, all the samples are transferred and used by a batch RL algorithm to solve the target task, but their contribution to the learning process is proportional to their importance weight. By extending the results for importance weighting provided in supervised learning literature, we develop a finite-sample analysis of the proposed batch RL algorithm. Furthermore, we empirically compare the proposed algorithm to state-of-the-art approaches, showing that it achieves better learning performance and is very robust to negative transfer, even when some source tasks are significantly different from the target task.

arXiv commentAccepted at ICML 2018

References in corpus (2)

• Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations
• An analytic comparison of regularization methods for Gaussian Processes

Cited by in corpus (10)

• Lifelong Incremental Reinforcement Learning with Online Bayesian Inference
• Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments
• MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics
• Lifelong Robotic Reinforcement Learning by Retaining Experiences
• AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning
• REPAINT: Knowledge Transfer in Deep Reinforcement Learning
• Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
• Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization
• Transfer Reinforcement Learning under Unobserved Contextual Information
• Time-Variant Variational Transfer for Value Functions