Research map / Multi-agent systems and games / Cooperative multi-agent RL
TMAE:Learning Targeted Multi-Agent Exploration via Causal Inference
Chuxiong Sun, Dunqi Yao, Rui Wang, Wenwen Qiang, Changwen Zheng, Jiangmeng Li
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 |
|---|---|---|---|
| add causal subspace weighting (ACE) to subspace intrinsic rewards (ablation) | TMAE · GRF academy 3 vs 1 with keeper; SMAC MMM2 | performance | Improved |
| add counterfactual intervention on actions (ablation) | TMAE · GRF scenarios | training stability | Improved |
| add intrinsic rewards (global RND or naive subspace) over epsilon-greedy QMIX (ablation) | QMIX · GRF academy 3 vs 1 with keeper; SMAC MMM2 | performance | Improved |
| replace global intrinsic reward with equal-weight subspace intrinsic rewards (ablation) | TMAE · GRF academy 3 vs 1 with keeper; SMAC MMM2 | performance | No clear effect |
| TMAE vs SOTA exploration baselines | TMAE · GRF and SMAC sparse-reward scenarios | exploration efficiency | Improved |
Closest papers by meaning
- Causal Information Prioritization for Efficient Reinforcement Learning (ICLR 2025 · similarity 0.88)
- DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
- Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- Hierarchical Reinforcement Learning with Targeted Causal Interventions (ICML 2025 · similarity 0.87)
- Situation-Dependent Causal Influence-Based Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.87)
- Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations (CVPR 2025 · 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.
