Transfer from Multiple MDPs

Abstract

Transfer reinforcement learning (RL) methods leverage on the experience collected on a set of source tasks to speed-up RL algorithms. A simple and effective approach is to transfer samples from source tasks and include them into the training set used to solve a given target task. In this paper, we investigate the theoretical properties of this transfer method and we introduce novel algorithms adapting the transfer process on the basis of the similarity between source and target tasks. Finally, we report illustrative experimental results in a continuous chain problem.

2011

Cited by in corpus (13)

• Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey
• Sample Complexity of Multi-task Reinforcement Learning
• Sharing Knowledge in Multi-Task Deep Reinforcement Learning
• Safe Reinforcement Learning via Curriculum Induction
• Clustering Markov Decision Processes For Continual Transfer
• Batch Policy Learning under Constraints
• On the Power of Multitask Representation Learning in Linear MDP
• Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
• Impact of Representation Learning in Linear Bandits
• Generalization Bounds for Representative Domain Adaptation
• PAC Bounds for Imitation and Model-based Batch Learning of Contextual Markov Decision Processes
• Transfer Reinforcement Learning under Unobserved Contextual Information
• Provably Efficient Multi-Task Reinforcement Learning with Model Transfer