Tag
This paper proposes SIGMA, a hierarchical collaboration framework for cooperative multi-agent reinforcement learning that learns robust representations under noisy observations by exploiting cooperation structures through density-based grouping and aggregation methods.
This paper introduces EpicStar, a framework that uses episodic memory and dynamic retrieval to help LLM agents maintain strategic coherence in long-horizon tasks like StarCraft II, achieving higher win rates with significantly fewer tokens.
Introduces a framework called Latent Maps of Performance for generating counterfactual feedback in StarCraft II using a Guided Variational Autoencoder trained on professional replays, enabling improvement trajectories for amateur players.