Research map / Multi-agent systems and games / Cooperative multi-agent RL
Who Matters Matters: Agent-Specific Conservative Offline MARL
Haosheng Chen, Yun Hua, Wenhao Li, Shiqin Wang, Xiangfeng Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add dynamic conservative degree allocation across agents (vs one shared degree) (ablation) | OMCDA · HalfCheetah (MA-MuJoCo) and 6h_vs_8z (SMAC) | average return | Improved |
| add Q-function decomposition into return and deviation parts (ablation) | OMCDA · HalfCheetah (MA-MuJoCo) and 6h_vs_8z (SMAC) | average return | Improved |
| use influence-based allocation instead of random per-agent conservative degrees (ablation) | OMCDA · HalfCheetah (MA-MuJoCo) and 6h_vs_8z (SMAC) | average return | Improved |
| use a smaller total conservative degree d_tot on high-quality datasets (ablation) | OMCDA · HalfCheetah and 6h_vs_8z, high-quality datasets | average return | Improved |
| dynamic (unequal) allocation of deviation vs uniform allocation in 2-player toy game | toy payoff game · 2-player example | expected team reward gain: 0.1 -> 0.15 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ComaDICE — ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (ICLR 2025) · better on 15 of 19 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (ICLR 2025 · similarity 0.91)
- Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL (AAAI 2025 · similarity 0.91)
- Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation (NeurIPS 2024 · similarity 0.90)
- Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization (AAAI 2025 · similarity 0.90)
- Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning (ICLR 2024 · similarity 0.88)
- Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank (ICLR 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
