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
Model-based RL and world models
Benchmarks: Atari 100k, DeepMind Control Suite, Crafter, Meta-World (multi-task) and others. Datasets: TD-MPC2 multi-task dataset, D4RL, rliable Atari 100k scores. Baselines: DreamerV3, TD-MPC2, MuZero, EfficientZero and others.