Pith. sign in

REVIEW 3 cited by

Causal Multi-Agent Reinforcement Learning: Review and Open Problems

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 2111.06721 v2 pith:ZSESYWXY submitted 2021-11-12 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords causalitymarlcausalchallengescontextdiscusslearningmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper serves to introduce the reader to the field of multi-agent reinforcement learning (MARL) and its intersection with methods from the study of causality. We highlight key challenges in MARL and discuss these in the context of how causal methods may assist in tackling them. We promote moving toward a 'causality first' perspective on MARL. Specifically, we argue that causality can offer improved safety, interpretability, and robustness, while also providing strong theoretical guarantees for emergent behaviour. We discuss potential solutions for common challenges, and use this context to motivate future research directions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

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

  1. CRRL: A Causality-Based Reinforcement Learning Framework for Autonomous System Recovery

    cs.SE 2026-07 conditional novelty 5.0 of 10

    Causal-guided PPO training produces policies that cooperate with rule-based recovery, yielding significant gains in reward, distance, and velocity over non-causal baselines in CARLA driving scenarios.

  2. Causality-informed Anomaly Detection in Partially Observable Sensor Networks: Moving beyond Correlations

    cs.AI 2025-07 reject novelty 5.0 of 10

    A deep Q-network that mixes causal statistics and a causality-weighted entropy term is proposed for placing sensors in partially observable anomaly detection.

  3. Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning

    cs.MA 2025-07 reject novelty 4.0 of 10

    A graph-RL driving agent using VGAE-based causal feature extraction achieves lower collision rates and higher rewards at a simulated unsignalized intersection than graph-RL baselines.

Pith tools