Poster Presentation: Learning to Plan with Tree Search via Deep RL

Research output: Contribution to conference typesPosterpeer-review

Abstract

Tree search is an important component of many decision-making algorithms but often relies on an evaluation function that estimates the desirability of each node. In this paper, we propose to learn which nodes to expand based on a variety of object-level features. We introduce a reward function for this problem based on value of computation estimates with respect to improving the policy for the underlying problem. We apply deep reinforcement learning to this problem in an approach we call Reinforcement Learning for Tree Search (RLTS) and demonstrate that it can yield better performance than baselines in a procedurally generated environment.
Original languageEnglish
Publication statusAccepted/In press - 20 Aug 2023
EventThe Bridging the Gap Between AI Planning and Reinforcement Learning Workshop at the International Joint Conference on AI - Macau, China
Duration: 20 Aug 202320 Aug 2023
https://prl-theworkshop.github.io/prl2023-ijcai/

Workshop

WorkshopThe Bridging the Gap Between AI Planning and Reinforcement Learning Workshop at the International Joint Conference on AI
Abbreviated titlePRL @ IJCAI 2023
Country/TerritoryChina
CityMacau
Period20/08/202320/08/2023
Internet address

Keywords

  • Reinforcement Learning
  • Planning Algorithms
  • Tree Search
  • Metareasoning

Fingerprint

Dive into the research topics of 'Poster Presentation: Learning to Plan with Tree Search via Deep RL'. Together they form a unique fingerprint.

Cite this