State Space Decomposition And Subgoal Creation For Transfer In Deep Reinforcement Learning

Abstract

Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, simpler domains to more complex ones using a recurrent attention mechanism. The task is presented to the agent as an image and an instruction specifying the goal. This meta-controller guides the agent towards its goal by designing a sequence of smaller subtasks on the part of the state space within the attention, effectively decomposing it. As a baseline, we consider a setup without attention as well. Our experiments show that the meta-controller learns to create subgoals within the attention.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysahni2017state

Related papers

• Transfer Reinforcement Learning In Heterogeneous Action Spaces Using Subgoal Mapping (2024)0.00
• State-conditioned Adversarial Subgoal Generation (2022)0.00
• Contextual Pre-planning On Reward Machine Abstractions For Enhanced Transfer In Deep Reinforcement Learning (2023)2.26
• Generalizing Skills With Semi-supervised Reinforcement Learning (2016)0.00
• Learning Complex Teamwork Tasks Using A Given Sub-task Decomposition (2023)0.00
• Goal Space Abstraction In Hierarchical Reinforcement Learning Via Reachability Analysis (2023)0.00
• Generating Adjacency-constrained Subgoals In Hierarchical Reinforcement Learning (2020)0.00
• Learning Representations In Model-free Hierarchical Reinforcement Learning (2018)11.49