Staging: a test copy of Stemma. Its data is wiped often and nothing here is paid for.

Stemma.

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

Meta-RL, multi-task RL and generalisation

Benchmarks: Meta-World (ML1/ML10/ML45, MT10/MT50), Meta-World+, Procgen generalisation, XLand-MiniGrid and others. Datasets: XLand-100B, TD-MPC2 multi-task dataset. Baselines: MAML, RL^2, PEARL, VariBAD and others.

No papers here yet