Research map / Multi-agent systems and games / Cooperative multi-agent RL
Deep Reinforcement Learning for Swarm Systems
Maximilian Hüttenrauch, Adrian Šošić, Gerhard Neumann
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 |
|---|---|---|---|
| use neural network mean embedding instead of max pooling (ablation) | pursuit-evasion policy · Pursuit-evasion | successful-catch trials: 4/16 -> 10/16 | Improved |
| use mean embedding instead of softmax pooling (ablation) | pursuit-evasion policy · Pursuit-evasion | successful-catch trials: 6/16 -> 10/16 | Improved |
| use neural network embedding NN+ with extended features instead of NN or RBF on basic set (ablation) | rendezvous policy · Rendezvous | average episode return: ~10 % better | Improved |
| use NN+ embedding instead of NN/RBF (ablation) | rendezvous policy · Rendezvous | steady-state mean distance: ~8e-2 -> ~4e-2 | Improved |
| use NN+ embedding instead of NN/RBF (ablation) | rendezvous policy · Rendezvous | time to reach reference distance: ~25 % | Improved |
| histogram/RBF embedding with extended feature set (ablation) | rendezvous policy · Rendezvous | success: did not succeed | Hurt |
| replace mean embedding with statistics (mean, std, skew, kurtosis) of features (ablation) | pursuit-evasion policy · Pursuit-evasion 50 agents 5 evaders | return | Hurt |
| compare learned policy to PD controller | rendezvous policy · Rendezvous | average reward | Improved |
Closest papers by meaning
- Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration (ICML 2025 · similarity 0.88)
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (ICLR 2024 · similarity 0.88)
- Learning Policy Representations in Multiagent Systems (ICML 2018 · similarity 0.88)
- Agent Modelling under Partial Observability for Deep Reinforcement Learning (NeurIPS 2021 · similarity 0.87)
- Hierarchical Mean-Field Deep Reinforcement Learning for Large-Scale Multiagent Systems (AAAI 2023 · similarity 0.87)
- Multi-agent In-context Coordination via Decentralized Memory Retrieval (AAAI 2026 · 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.
