Sharing Knowledge in Multi-Task Deep Reinforcement Learning

Abstract

We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption that learning from different tasks, sharing common properties, is helpful to generalize the knowledge of them resulting in a more effective feature extraction compared to learning a single task. Intuitively, the resulting set of features offers performance benefits when used by Reinforcement Learning algorithms. We prove this by providing theoretical guarantees that highlight the conditions for which is convenient to share representations among tasks, extending the well-known finite-time bounds of Approximate Value-Iteration to the multi-task setting. In addition, we complement our analysis by proposing multi-task extensions of three Reinforcement Learning algorithms that we empirically evaluate on widely used Reinforcement Learning benchmarks showing significant improvements over the single-task counterparts in terms of sample efficiency and performance.

References in corpus (1)

• Theoretical Models of Learning to Learn

Cited by in corpus (8)

• Near-optimal Representation Learning for Linear Bandits and Linear RL
• On the Power of Multitask Representation Learning in Linear MDP
• Linear Representation Meta-Reinforcement Learning for Instant Adaptation
• Conservative Data Sharing for Multi-Task Offline Reinforcement Learning
• Distill Knowledge in Multi-task Reinforcement Learning with Optimal-Transport Regularization
• PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes
• Multitasking Inhibits Semantic Drift
• Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning