rubix
PublicDeep Reinforcement Learning based Rubik’s Cube solver written in JAX, Haiku and RLax. Developed a custom environment supporting cubes of variable size. Currently developing support for DQN, QR-DQN and PPO.
Creat:2023-03-14T20:47:03
Update:2023-04-11T23:13:19
1
Stars
0
Stars Increase