pith. sign in

arxiv: 2304.12000 · v1 · pith:RKTD25WSnew · submitted 2023-04-24 · 💻 cs.AI

Hierarchical State Abstraction Based on Structural Information Principles

classification 💻 cs.AI
keywords stateabstractioninformationhierarchicalsisastructuralapproachesessential
0
0 comments X
read the original abstract

State abstraction optimizes decision-making by ignoring irrelevant environmental information in reinforcement learning with rich observations. Nevertheless, recent approaches focus on adequate representational capacities resulting in essential information loss, affecting their performances on challenging tasks. In this article, we propose a novel mathematical Structural Information principles-based State Abstraction framework, namely SISA, from the information-theoretic perspective. Specifically, an unsupervised, adaptive hierarchical state clustering method without requiring manual assistance is presented, and meanwhile, an optimal encoding tree is generated. On each non-root tree node, a new aggregation function and condition structural entropy are designed to achieve hierarchical state abstraction and compensate for sampling-induced essential information loss in state abstraction. Empirical evaluations on a visual gridworld domain and six continuous control benchmarks demonstrate that, compared with five SOTA state abstraction approaches, SISA significantly improves mean episode reward and sample efficiency up to 18.98 and 44.44%, respectively. Besides, we experimentally show that SISA is a general framework that can be flexibly integrated with different representation-learning objectives to improve their performances further.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Structure-Induced Information for Rerooting Levin Tree Search

    cs.AI 2026-05 unverdicted novelty 6.0

    Three rerooter designs (clustering-based, heuristic-based, hybrid) for √LTS enable scalable search in complex single-agent environments where explicit subgoal methods fail and achieve SOTA online training efficiency.