Hierarchical reinforcement Thompson composition

Date

2024-01-01

Author

Tanık, Güven Orkun
Ertekin Bolelli, Şeyda

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

17
views

1
downloads

Cite This

Modern real-world control problems call for continuous control domains and robust, sample efficient and explainable control frameworks. We are presenting a framework for recursively composing control skills to solve compositional and progressively complex tasks. The framework promotes reuse of skills, and as a result quick adaptability to new tasks. The decision tree can be observed, providing insight into the agents’ behavior. Furthermore, the skills can be transferred, modified or trained independently, which can simplify reward shaping and increase training speeds considerably. This paper is concerned with efficient composition of control algorithms using reinforcement learning and soft attention. Compositional and temporal abstraction is the key to improving learning and planning in reinforcement learning. Our Thompson sampling inspired soft-attention model is demonstrated to efficiently solve the composition problem.

Subject Keywords

Artificial intelligence agents, Reinforcement learning, Soft attention, Thompson sampling

URI

https://hdl.handle.net/11511/109760

Collections

Department of Computer Engineering, Article