2023/06/08 by Noémi Éltető, Peter Dayan, Éltető, Noémi +1
Computer Science · #AI-based Problem Solving and Planning #Artificial Intelligence in Games #Machine Learning and Algorithms
paper · pdf · doi:10.48550/arxiv.2306.05298
When we exercise sequences of actions, their execution becomes more fluent and precise. Here, we consider the possibility that exercised action sequences can also be used to make planning faster and more accurate by focusing expansion of the search tree on paths that have been frequently used in the past, and by reducing deep planning problems to shallow ones via multi-step jumps in the tree. To capture such sequences, we use a flexible Bayesian action chunking mechanism which finds and exploits statistically reliable structure at different scales. This gives rise to shorter or longer routines that can be embedded into a Monte-Carlo tree search planner. We show the benefits of this scheme using a physical construction task patterned after tangrams.