Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Trajectory Diversity for Zero-Shot Coordination
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 |
|---|---|---|---|
| Add TrajeDi diversity regularization to the population used to train the common BR | OP pool BR in Hanabi · Hanabi (hint-hidden, OP) | XP score: +0.43 (24.09 vs 23.66) | Helped |
| Add TrajeDi diversity regularization to the population used to train the common BR | OP pool BR in Hanabi · Hanabi (hint-hidden, OP) | SP score: -0.05 (24.22 vs 24.17 is actually higher; SP drop noted vs individual agents) | Hurt |
| Train common BR to a diverse (TrajeDi) population instead of unregularized population in matrix game | Common BR in single-step matrix game · Matrix game | XP return | Helped |
| Add TrajeDi objective to population training in toy MDP trees (ablation) | Policy populations in complete and incomplete trees · Toy trees (trajectory diversity) | trajectory coverage of all solutions | Helped |
| Use entropic initialization instead of random initialization with TrajeDi (ablation) | TrajeDi populations in toy trees · Complete tree | fraction of runs finding every solution | Helped |
| Raise TrajeDi weight alpha to 4 (ablation) | TrajeDi populations in incomplete tree · Incomplete tree | optimality of trajectories | Hurt |
Closest papers by meaning
- Learning Diverse Risk Preferences in Population-Based Self-Play (AAAI 2024 · similarity 0.89)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.89)
- Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners (NeurIPS 2024 · similarity 0.89)
- ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination (NeurIPS 2024 · similarity 0.89)
- Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.88)
- OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination (ICLR 2025 · 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.