Research map / Multi-agent systems and games / Cooperative multi-agent RL
Subspace-Aware Exploration for Sparse-Reward Multi-Agent Tasks
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 SAME's sub-state-space exploration bonus | SAME · MPE, SMAC, and GRF sparse-reward tasks | sample efficiency | Helped |
| Add the sub-state-space bonus instead of setting it to a constant 1 (ablation) | SAME · Ablation tasks in Figure 6 | task performance | Helped |
| Weight sub-state spaces by uncertainty rather than using the vanilla sub-state-space bonus (ablation) | SAME · Ablation tasks in Figure 6 | task performance | Helped |
| Add local restrictions to the full-state-space bonus (ablation) | SAME · Ablation tasks in Figure 6 | exploration performance | Helped |
| Use SAME for exploration | SAME · MPE sparse-reward tasks | sample efficiency | Helped |
| Use SAME for exploration | SAME · SMAC sparse-reward tasks | task success | Helped |
| Use SAME for exploration | SAME · GRF sparse-reward tasks | task performance | Helped |
| Use SAME in tasks with more agents | SAME · SMAC 10m vs 11m and 27m vs 30m | task success | Helped |
Closest papers by meaning
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.90)
- Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning (ICML 2024 · similarity 0.87)
- Action-Dependent Optimality-Preserving Reward Shaping (ICML 2025 · similarity 0.87)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.86)
- The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration (NeurIPS 2026 · similarity 0.86)
- Settling Decentralized Multi-Agent Coordinated Exploration by Novelty Sharing (AAAI 2024 · similarity 0.86)
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.