Fields
Pick a domain and keep going deeper: field, subfield, topic. Every step lists the papers at that point or below it. The counts are papers that are accepted or in review; papers that were not accepted are in the full library.
Subfield
Game-theoretic learning and zero-shot coordination
Benchmarks: Hanabi (self-play, cross-play, ad hoc), Overcooked-AI layouts, Melting Pot 2.0, OpenSpiel poker and matrix games and others. Datasets: Overcooked human-human trajectories. Baselines: Other-Play, SAD, Off-Belief Learning, Fictitious Co-Play and others.