MetaGym provides abundant environments for benchmarking Reinforcement Learning and Meta Reinforcement Learning
-
LiftSim：Simulator for Evelvator Dispatching (Sep, 2019)
-
Quadrotor: 3D Quadrotor simulator for different tasks (Mar, 2020)
-
Quadrupedal: Quadrupedal robot adapting to different terrains (Seq, 2021)
-
MetaMaze: 2D/3D maze generators for task generalization (Oct, 2021)
-
MetaLocomotion: Locomotion simulator with diverse geometries (June, 2022)
-
MetaLM: Meta language model dataset (Dec, 2022)
-
Bandits: Bandits task generalization (Dec, 2022)