Research map / Multi-agent systems and games / Cooperative multi-agent RL
LIIR: Learning Individual Intrinsic Reward in 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 |
|---|---|---|---|
| learn individual intrinsic reward per agent (LIIR) on top of actor-critic | MARL with centralized critic · StarCraft II 3M, 8M, 2S3Z, 3S5Z | test win rate: around 90% winning rate in all scenarios | Helped |
| use centralized critic (CLDE) instead of independent learning (IQL, IAC) | MARL baselines · StarCraft II 8M, 2S3Z, 3S5Z | test win rate | Helped |
| vary lambda weight of intrinsic reward (ablation) | LIIR · StarCraft II | test win rate | No clear effect |
Closest papers by meaning
- LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning (ICLR 2022 · similarity 0.90)
- Individual Reward Assisted Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.89)
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.88)
- Coordination Between Individual Agents in Multi-Agent Reinforcement Learning (AAAI 2021 · similarity 0.88)
- Learning to Incentivize Other Learning Agents (NeurIPS 2020 · similarity 0.88)
- Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning (ICML 2024 · similarity 0.87)
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.