Research map / Multi-agent systems and games / Cooperative multi-agent RL
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning
Kyunghwan Son, Junsu Kim, Sungsoo Ahn, Roben D Delos Reyes, Yung Yi, Jinwoo Shin
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| set DMIX risk sensitivity from neutral to seeking (ablation) | DMIX · Stochastic two-step matrix game | test reward: -0.02 -> 0.03 | No clear effect |
| disentangle cooperative (seeking) and environmental (neutral) risk using DRIMA instead of DMIX | DRIMA · Stochastic two-step matrix game | test reward: 0.03 -> 6.98 | Improved |
| disentangle risk sources in DRIMA versus eight baselines | DRIMA · SMAC explorative and dilemmatic scenarios | battle won mean | Improved |
| cooperative risk-neutral instead of seeking in DRIMA (environment seeking) (ablation) | DRIMA · SMAC MMM2-v1 | battle won mean | Hurt |
| environmental risk neutral or averse instead of seeking in DRIMA (ablation) | DRIMA · SMAC MMM2-v1 | battle won mean | Hurt |
| risk-sensitive variants of DDN and DMIX (quantile range [0, 0.25] averse, [0.75, 1] seeking) versus DRIMA (ablation) | DDN and DMIX · SMAC MMM2-v1 | battle won mean | Hurt |
| vary environmental risk level (seeking, neutral, averse) on easy tasks (ablation) | DRIMA · 5m_vs_6m, 3s_vs_5z, 8m_vs_9m | battle won mean | No clear effect |
| environmental risk-averse setting (ablation) | DRIMA · 8m_vs_9m-v1 | win rate | Improved |
| control risk sensitivity with random or adversarial noisy agents | DRIMA · SMAC 3s_vs_5z and 5m_vs_6m noisy | battle won mean | Improved |
Closest papers by meaning
- Training Generalizable Collaborative Agents via Strategic Risk Aversion (NeurIPS 2026 · similarity 0.88)
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.87)
- Robust and Diverse Multi-Agent Learning via Rational Policy Gradient (NeurIPS 2025 · similarity 0.87)
- Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Test-time Risk Adaptation with Mixture of Agents (NeurIPS 2026 · similarity 0.87)
- Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty (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.
