Pith. sign in

REVIEW 7 cited by

Robust agents learn causal world models

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 2402.10877 v7 pith:AQLXV5MU submitted 2024-02-16 cs.AI cs.LG

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

It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Calculating Mutual Information between a Reward Maximizer and its Environment

    cs.AI 2026-02 conditional novelty 6.0 of 10

    Under a uniform prior over transition probabilities, the mutual information between a controlled Markov process and its optimal deterministic policy is exactly n log m bits for discounted, finite-horizon (with caveats...

  2. Enhancing LLM Agent Safety via Causal Influence Prompting

    cs.AI 2025-07 conditional novelty 6.0 of 10

    CIP, which makes LLM agents construct and refine a causal influence diagram before acting, raises refusal rates on harmful tasks in three agent-safety benchmarks.

  3. The Limits of Predicting Agents from Behaviour

    cs.AI 2025-06 accept novelty 6.0 of 10

    Observed behavior only weakly constrains an intentional agent's choices under distribution shift, and its perceived fairness and harm cannot be identified from behavior alone.

  4. 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.

  5. Linear Spatial World Models Emerge in Large Language Models

    cs.AI 2025-06 reject novelty 5.0 of 10

    Spatial relation words in LLaMA and Qwen models form antipodal, roughly orthogonal directions in a low-dimensional subspace, and steering along these directions changes the model's output.

  6. Causal Information Prioritization for Efficient Reinforcement Learning

    cs.AI 2025-02 reject novelty 5.0 of 10

    CIP combines DirectLiNGAM-style causal masks for state-reward and action-reward links with counterfactual data augmentation and an empowerment objective to improve RL sample efficiency.

  7. The Generalist Brain Module: Module Repetition in Neural Networks in Light of the Minicolumn Hypothesis

    q-bio.NC 2025-07 conditional novelty 4.0 of 10

    A review arguing that repeating a single generalist neural module, inspired by cortical minicolumns, yields robustness, scalability, and generalization benefits compared to monolithic networks.

Pith tools