paper-with-me

홈 › Papers

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

2024-01-23 · Zizhao Wang, Caroline Wang, Xuesu Xiao, Yuke Zhu, Peter Stone

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is to learn state abstractions, which only keep the necessary variables for learning the tasks at hand. This paper introduces Causal Bisimulation Modeling (CBM), a method that learns the causal relationships in the dynamics and reward functions for each task to derive a minimal, task-specific abstraction. CBM leverages and improves implicit modeling to train a high-fidelity causal dynamics model that can be reused for all tasks in the same environment. Empirical validation on manipulation environments and Deepmind Control Suite reveals that CBM's learned implicit dynamics models identify the underlying causal relationships and state abstractions more accurately than explicit ones. Furthermore, the derived state abstractions allow a task learner to achieve near-oracle levels of sample efficiency and outperform baselines on all tasks.

📄 PDF Abstract BibTeX arXiv:2401.12497

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents

2026-01-31 · Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum, Christopher J. Bates 외 arxiv

Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM) agents and deep reinforcement learning …

Reinforcement Learning

Property-driven Causal Abstractions for Markov Decision Processes

2026-07-29 · Jule Schmidt, Maximilian Weininger, Clemens Dubslaff, David Parker 외 arxiv

Markov Decision Processes (MDPs) are widely used as decision-making models, commonly specified over factored state spaces through state variables and their valuations. The exponential blowup in the number of states rende…

Causal Abstractions, Categorically Unified

2025-10-06 · Markus Englberger, Devendra Singh Dhami arxiv

We present a categorical framework for relating causal models that represent the same system at different levels of abstraction. We define a causal abstraction as natural transformations between appropriate Markov functo…

Aligning Graphical and Functional Causal Abstractions

2024-12-22 · Willem Schooltink, Fabio Massimo Zennaro

Causal abstractions allow us to relate causal models on different levels of granularity. To ensure that the models agree on cause and effect, frameworks for causal abstractions define notions of consistency. Two distinct…

The Causal Information Bottleneck and Optimal Causal Variable Abstractions

2024-10-01 · Francisco N. F. Q. Simoes, Mehdi Dastani, Thijs van Ommen

To effectively study complex causal systems, it is often useful to construct abstractions of parts of the system by discarding irrelevant details while preserving key features. The Information Bottleneck (IB) method is a…

Representation Learning