Pith. sign in

REVIEW 5 cited by

Causal Dynamics Learning for Task-Independent State Abstraction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.13452 v1 pith:SOSEUBOJ submitted 2022-06-27 cs.LG

classification cs.LG
keywords dynamicsstateabstractionlearningcausalmodelstatesunseen
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning dynamics models accurately is an important goal for Model-Based Reinforcement Learning (MBRL), but most MBRL methods learn a dense dynamics model which is vulnerable to spurious correlations and therefore generalizes poorly to unseen states. In this paper, we introduce Causal Dynamics Learning for Task-Independent State Abstraction (CDL), which first learns a theoretically proved causal dynamics model that removes unnecessary dependencies between state variables and the action, thus generalizing well to unseen states. A state abstraction can then be derived from the learned dynamics, which not only improves sample efficiency but also applies to a wider range of tasks than existing state abstraction methods. Evaluated on two simulated environments and downstream tasks, both the dynamics model and policies learned by the proposed method generalize well to unseen states and the derived state abstraction improves sample efficiency compared to learning without it.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Physics-guided residual dynamics, a spring-mass simulator plus a network that predicts velocity corrections, yields the most accurate deformable-object simulation in the paper's real-world tests.

  2. Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Closed-loop agentic probing plus minimality/sufficiency masking recovers compact task-sufficient world-model latents that improve sample-efficient policy learning and cross-task generalization.

  3. Factored Latent Action World Models

    cs.LG 2026-02 conditional novelty 6.0 of 10

    FLAM splits a scene into separate factors, each with its own latent action, and reports better video prediction and downstream policy learning than monolithic latent-action models.

  4. Learning Causal Structure Distributions for Robust Planning

    cs.RO 2025-08 conditional novelty 6.0 of 10

    Sampling causal structure hypotheses from a feature-attribution-derived distribution, instead of committing to a single causal graph, makes learned robot dynamics models more robust to noise and change at a fraction o...

  5. Towards Empowerment Gain through Causal Structure Learning in Model-Based RL

    cs.AI 2025-02 conditional novelty 6.0 of 10

    A model-based RL framework that alternates causal structure learning with empowerment-driven exploration, plus a curiosity reward, improves sample efficiency and asymptotic performance in six environments.

Pith tools