Transfer Reinforcement Learning In Heterogeneous Action Spaces Using Subgoal Mapping

Abstract

In this paper, we consider a transfer reinforcement learning problem involving agents with different action spaces. Specifically, for any new unseen task, the goal is to use a successful demonstration of this task by an expert agent in its action space to enable a learner agent learn an optimal policy in its own different action space with fewer samples than those required if the learner was learning on its own. Existing transfer learning methods across different action spaces either require handcrafted mappings between those action spaces provided by human experts, which can induce bias in the learning procedure, or require the expert agent to share its policy parameters with the learner agent, which does not generalize well to unseen tasks. In this work, we propose a method that learns a subgoal mapping between the expert agent policy and the learner agent policy. Since the expert agent and the learner agent have different action spaces, their optimal policies can have different subg

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysivakumar2024transfer

Related papers

• State Space Decomposition And Subgoal Creation For Transfer In Deep Reinforcement Learning (2017)0.00
• Contextual Policy Transfer In Reinforcement Learning Domains Via Deep Mixtures-of-experts (2020)0.00
• Similarity-based Knowledge Transfer For Cross-domain Reinforcement Learning (2023)0.00
• Deep Multi-agent Reinforcement Learning With Discrete-continuous Hybrid Action Spaces (2019)12.47
• Diversity For Contingency: Learning Diverse Behaviors For Efficient Adaptation And Transfer (2023)0.00
• Toward Robust Long Range Policy Transfer (2021)0.00
• Growing Action Spaces (2019)0.00
• Investigating The Role Of Model-based Learning In Exploration And Transfer (2023)0.00