Research map / Multi-agent systems and games / Cooperative multi-agent RL
Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic
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 DSAC for entropy-based exploration instead of MaxEnt | Cooperative navigation, 2 agents · Cooperative navigation exploration | space coverage | Helped |
| Decentralize the actor-critic and use marginalized occupancy measures | DSAC · Cooperative navigation exploration | exploration performance | No clear effect |
| Impose occupancy-measure safety constraints using a quadratic penalty | DSAC · Safe cooperative navigation, 2 agents | constraint violation | Helped |
| Use DSAC with safety constraints instead of the alternative methods | Safe cooperative navigation, 2 agents · Safe cooperative navigation | average reward | Helped |
| Allow multiple communication rounds per policy update instead of one | DSAC · General-utility MARL theoretical analysis | sample complexity: O(ϵ−2.5) to O(ϵ−2) | Helped |
Closest papers by meaning
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.90)
- Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games (ICLR 2022 · similarity 0.90)
- Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward (ICLR 2022 · similarity 0.89)
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NeurIPS 2017 · similarity 0.89)
- Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization (NeurIPS 2018 · similarity 0.89)
- Multi-Agent Reinforcement Learning with Submodular Reward (ICML 2026 · similarity 0.89)
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.