PaddlePaddle/MetaGym

PaddlePaddle/MetaGym

Description: Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

Language: Python

License: Apache-2.0

Stars: 302

Forks: 61

Open issues: 13

Created: 2019-07-13T16:37:35Z

Pushed: 2024-07-15T17:29:11Z

Default branch: master

Fork: no

Archived: no

README:

MetaGym

MetaGym provides abundant environments for benchmarking Reinforcement Learning and Meta Reinforcement Learning

Environments Updating

• [LiftSim](metagym/liftsim)：Simulator for Evelvator Dispatching (Sep, 2019)

• [Quadrotor](metagym/quadrotor): 3D Quadrotor simulator for different tasks (Mar, 2020)

• [Quadrupedal](metagym/quadrupedal): Quadrupedal robot adapting to different terrains (Seq, 2021)

• [MetaMaze](metagym/metamaze): 2D/3D maze generators for task generalization (Oct, 2021)

• [MetaLocomotion](metagym/metalocomotion): Locomotion simulator with diverse geometries (June, 2022)

• [MetaLM](metagym/metalm): Meta language model dataset (Dec, 2022)

• [Bandits](metagym/bandits): Bandits task generalization (Dec, 2022)