Timezone: »

Learning Action Representations for Reinforcement Learning
Yash Chandak · Georgios Theocharous · James Kostas · Scott Jordan · Philip Thomas

Tue Jun 11 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #112

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be decomposed into a component that acts in a low-dimensional space of action representations and a component that transforms these representations into actual actions. These representations improve generalization over large, finite action sets by allowing the agent to infer the outcomes of actions similar to actions already taken. We provide an algorithm to both learn and use action representations and provide conditions for its convergence. The efficacy of the proposed method is demonstrated on large-scale real-world problems.

Author Information

Yash Chandak (University of Massachusetts Amherst)
Georgios Theocharous (Adobe Research)
James Kostas (UMass Amherst)
Scott Jordan (University of Massachusetts Amherst)
Philip Thomas (University of Massachusetts Amherst)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors