Adaptive Coalition Structure Generation

Abstract

We introduce a Deep Reinforcement Learning (DRL) framework to form socially-optimal coalitions in an adaptive manner. In our approach, agents play a deal-or-no-deal game where each state represents a potential coalition to join. Agents learn to form coalitions that are mutually beneficial, without revealing the coalition value to each other. We conducted an empirical evaluation of our model's generalizability on a ridesharing spatial game.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Cipolina-Kun et al. "Adaptive Coalition Structure Generation." NeurIPS 2023 Workshops: ALOE, 2023.

Markdown

[Cipolina-Kun et al. "Adaptive Coalition Structure Generation." NeurIPS 2023 Workshops: ALOE, 2023.](https://mlanthology.org/neuripsw/2023/cipolinakun2023neuripsw-adaptive/)

BibTeX

@inproceedings{cipolinakun2023neuripsw-adaptive,
  title     = {{Adaptive Coalition Structure Generation}},
  author    = {Cipolina-Kun, Lucia and Carlucho, Ignacio and Bullard, Kalesha},
  booktitle = {NeurIPS 2023 Workshops: ALOE},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/cipolinakun2023neuripsw-adaptive/}
}