Research map / Reinforcement learning / Policy gradient and actor-critic
Credit Assignment For Collective Multiagent RL With Global Rewards
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 MCAC (marginalize out state-action counts) instead of MIP static allocation | police patrolling · Police patrolling | incidents over response threshold (%): 9.32% -> 7.8% | Helped |
| use MCAC instead of CCAC (ablation) | collective actor critic · Police patrolling (sparse counts) | objective value | Helped |
| use MCAC instead of CCAC (ablation) | collective actor critic · Synthetic grid patrolling (M=5 to 50) | quality | Helped |
| use MCAC instead of CCAC (ablation) | collective actor critic · Taxi, M=8000 (dense counts) | quality | No clear effect |
| use MCAC/CCAC instead of factored actor-critic fAfC as QoS penalty weight w grows | taxi fleet optimization · Taxi supply-demand | quality | Helped |
| increase QoS penalty w from 0 to 1 in MCAC (ablation) | MCAC · Taxi supply-demand | unserved demand: decreased by 32% | Helped |
| use counterfactual advantage A_ij instead of Q_ij in gradient (ablation) | CCAC · collective domains | solution quality | Helped |
| use difference rewards (CCAC) with small agent population (ablation) | CCAC · small populations (M=5) | solution quality | Hurt |
Closest papers by meaning
- COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams (NeurIPS 2026 · similarity 0.86)
- STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents (NeurIPS 2025 · similarity 0.86)
- Multi Agent Reinforcement Learning for Sequential Satellite Assignment Problems (AAAI 2025 · similarity 0.85)
- LNS2+RL: Combining Multi-agent Reinforcement Learning with Large Neighborhood Search in Multi-agent Path Finding (AAAI 2025 · similarity 0.85)
- Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning (NeurIPS 2026 · similarity 0.85)
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.