Pith. sign in

REVIEW 18 cited by

Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2006.07869 v4 pith:ABIRKBBT submitted 2020-06-14 cs.LG cs.AIcs.MAstat.ML

Georgios Papoudakis , Filippos Christianos , Lukas Schäfer , Stefano V. Albrecht This is my paper · ORCID
classification cs.LGcs.AIcs.MAstat.ML
keywords learningmulti-agentalgorithmstasksdifferentapproachescooperativedeep
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different classes of MARL algorithms (independent learning, centralised multi-agent policy gradient, value decomposition) in a diverse range of cooperative multi-agent learning tasks. Our experiments serve as a reference for the expected performance of algorithms across different learning tasks, and we provide insights regarding the effectiveness of different learning approaches. We open-source EPyMARL, which extends the PyMARL codebase to include additional algorithms and allow for flexible configuration of algorithm implementation details such as parameter sharing. Finally, we open-source two environments for multi-agent research which focus on coordination under sparse rewards.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

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

  1. MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Credit assignment via LMM pairwise comparisons plus Bradley–Terry rank aggregation and potential-based shaping improves cooperative MARL under sparse rewards and dynamic agent counts.

  2. Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning

    cs.LG 2026-06 conditional novelty 6.0 of 10

    Certified local LTL_safe contracts, jointly fixed-point checked and selected by a bandit, recover coordinated safe team policies under decentralised multi-agent RL execution.

  3. Multi-Agent Reinforcement Learning for V2X Resource Allocation: Disentangling MARL Challenges Through Benchmarking

    cs.MA 2026-02 conditional novelty 6.0 of 10

    Robustness to varied vehicle topologies, not partial observability or coordination, is the dominant obstacle for MARL in C-V2X spectrum sharing.

  4. Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A new transformer-based multi-agent world model with teammate prediction and prioritized replay achieves near-optimal performance on cooperative benchmarks in as few as 50,000 environment steps.

  5. Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour

    cs.AI 2025-05 conditional novelty 6.0 of 10

    AXIS couples an LLM with a multi-agent simulator to produce counterfactual action explanations, and reports higher judged correctness and goal-prediction accuracy than baselines on ten autonomous-driving scenarios.

  6. Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration

    cs.LG 2025-05 conditional novelty 6.0 of 10

    SMPE2 augments the MAA2C multi-agent actor-critic with per-agent variational state-belief inference, learnable observation filters, and count-based intrinsic exploration, and reports improved performance on MPE, LBF, ...

  7. ColorGrid: A Multi-Agent Non-Stationary Environment for Goal Inference and Assistance

    cs.AI 2025-01 conditional novelty 6.0 of 10

    A new benchmark shows that IPPO, a standard MARL algorithm, cannot reliably infer a partner's changing goal from its actions alone.

  8. Deterministic Model of Incremental Multi-Agent Boltzmann Q-Learning: Transient Cooperation, Metastability, and Oscillations

    cs.MA 2024-12 conditional novelty 6.0 of 10

    A frequency-aware mean-field model of incremental Boltzmann Q-learning in the Prisoner's Dilemma predicts that apparent stable cooperation is a long metastable transient and that high discount factors induce oscillati...

  9. Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems

    cs.MA 2024-12 conditional novelty 6.0 of 10

    REDA learns per-agent Q-values and uses them as benefit inputs to an optimal assignment mechanism, outperforming IQL, IPPO, COMA, and HAAL on sequential satellite assignment.

  10. Multi-Agent System for Cosmological Parameter Analysis

    astro-ph.IM 2024-11 conditional novelty 6.0 of 10

    A multi-agent LLM system with retrieval and local code execution reproduced ACT DR6 lensing cosmological parameter constraints without human-written code, and generalized to two research-software tasks.

  11. Explaining Reinforcement Learning Agents via Inductive Logic Programming

    cs.AI 2026-07 conditional novelty 5.0 of 10

    This paper introduces activation rate, feature coverage, syntactic distance, and semantic distance as objective metrics for logic-rule explanations of RL and multi-agent RL policies.

  12. cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending

    cs.LG 2025-08 reject novelty 5.0 of 10

    cMALC-D uses an LLM to generate training contexts for multi-agent RL and a diversity-blending mechanism to avoid mode collapse, claiming improved generalization on traffic signal control.

  13. Remembering the Markov Property in Cooperative MARL

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Cooperative MARL agents solve many benchmarks with brittle conventions that bypass observations and memory, so the field needs tasks that genuinely require grounded, history-based reasoning.

  14. From General Relation Patterns to Task-Specific Decision-Making in Continual Multi-Agent Coordination

    cs.MA 2025-07 conditional novelty 5.0 of 10

    RPG uses a relation capturer plus a task-conditioned hypernetwork to reduce catastrophic forgetting and enable zero-shot transfer in continual multi-agent coordination.

  15. PAGNet: Pluggable Adaptive Generative Networks for Information Completion in Multi-Agent Communication

    cs.MA 2025-02 conditional novelty 5.0 of 10

    PAGNet learns per-agent communication weights and generates global states with a U-Net and GAN discriminator, reporting improved cooperative MARL performance on LBF, Hallway, and SMAC.

  16. HIVEX: A High-Impact Environment Suite for Multi-Agent Research (extended version)

    cs.MA 2025-01 conditional novelty 5.0 of 10

    HIVEX is an open-source benchmark with five Unity-based multi-agent environments for ecological tasks, plus trained PPO baselines and a Hugging Face leaderboard.

  17. Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning

    cs.MA 2025-01 conditional novelty 5.0 of 10

    A decentralized MARL method that communicates observation-prediction error as an auxiliary message improves performance on out-of-distribution warehouse tasks.

  18. Feedback Attribution and Representation Geometry: Metrics for Comparing Individual and Shared Rewards in MARL

    cs.LG 2026-07 conditional novelty 4.0 of 10

    On SMACv2, role geometry in shared-encoder MARL is set by whether unit type is observed, not by individual vs shared reward; reward attribution affects behavior, mainly action diversity.

Pith tools