Reinforcement learning agent Roboschool Walker2d trained with
Proximal Policy Optimization ([ Ссылка ]).
The source code for training is available on Github: [ Ссылка ]
Ещё видео!
Reinforcement learning agent Roboschool Walker2d trained with
Proximal Policy Optimization ([ Ссылка ]).
The source code for training is available on Github: [ Ссылка ]