# Habits of Mind: Reusing Action Sequences for Efficient Planning

arXiv: https://arxiv.org/abs/2306.05298 · HTML: https://mlsanity.com/paper/2306.05298/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 21 references that are in the map.
- First posted on arXiv 8 Jun 2023.

## Builds on (most cited first, 3 of 3)

- [Eigenoption Discovery through the Deep Successor Representation](https://mlsanity.com/paper/1710.11089/) (2017)
- [Temporal Abstraction in Reinforcement Learning with the Successor Representation](https://mlsanity.com/paper/2110.05740/) (2021)
- [Structured agents for physical construction](https://mlsanity.com/paper/1904.03177/) (2019)

## Built on by (most cited first, 1 of 1)

- [Exploring the hierarchical structure of human plans via program generation](https://mlsanity.com/paper/2311.18644/) (2023)

## Abstract (arXiv)

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.