Research map / Multi-agent systems and games / Cooperative multi-agent RL
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use ICQ-MA with decomposed implicit-constraint policy learning instead of standard offline multi-agent baselines | Offline StarCraft II tasks · StarCraft II ten-map benchmark | performance | Helped |
| Use implicit-constraint Q-value estimation rather than Q(λ) or Tree Backup estimation (ablation) | ICQ-MA · MMM map, StarCraft II | performance | Helped |
| Add the decomposed implicit-constraint module (ablation) | ICQ-MA · MMM map, StarCraft II | performance | Helped |
| Use multi-step estimation rather than one-step estimation (ablation) | ICQ-MA · MMM map, StarCraft II | performance | No clear effect |
| Use an intermediate α rather than the limiting settings α→0 or α→∞ (ablation) | ICQ-MA · MMM map, StarCraft II | performance | Helped |
| Use ICQ-MA rather than behavior cloning as data quality deteriorates | Offline multi-agent learning · StarCraft II, varying data quality | performance | Helped |
Closest papers by meaning
- Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization (AAAI 2025 · similarity 0.89)
- C2IQL: Constraint-Conditioned Implicit Q-learning for Safe Offline Reinforcement Learning (ICML 2025 · similarity 0.89)
- Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning (NeurIPS 2025 · similarity 0.89)
- Exclusively Penalized Q-learning for Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.89)
- ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (ICLR 2025 · similarity 0.88)
- Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning (NeurIPS 2024 · 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.