Research map / Multi-agent systems and games / Cooperative multi-agent RL

Rethinking Credit Assignment in Cooperative MARL via Interventional Reward Response

NeurIPS 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies credit assignment in cooperative MARL under partial observability and proposes an interventional reward-response approach to estimate each agent's contribution; abstract only, so details are limited.

Problem

Credit assignment in cooperative multi-agent reinforcement learning under partial observability, where policy updates from global rewards and observational value estimates may not reflect each agent's actual contribution to team outcomes.

Approach

Uses interventional reward response to measure individual agent contributions, as opposed to relying on observational value estimates and global-reward policy gradients used by MAPPO and IPPO. Full method details are not available from the abstract.

Experimental setup

Baselines: MAPPO IPPO

Builds on: MAPPO IPPO

Closest papers by meaning

• COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams (NeurIPS 2026 · similarity 0.89)
• Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2020 · similarity 0.88)
• A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
• STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
• Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
• Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning (AAAI 2025 · similarity 0.87)