myGym
PublicmyGym enables fast prototyping of RL in the area of robotic manipulation and navigation.You can train different robots, in several environments on various tasks. There is automatic evaluation and benchmark tool. From version 2.1 there is support for multi-step tasks, multi-reward training and multi-network architectures.
deep-learningmulti-networkmulti-step-rlpick-and-placereal-timereinforcement-learningrobotic-manipulationroboticsrobotics-simulationsemantic-segmentation
Creat：2020-12-22T19:34:41
Update：2024-11-12T01:20:39
https://mygym.readthedocs.io/en/latest/
52
Stars
0
Stars Increase