Koha9 895cd5c118 Add EndReward Broadcast function ...

while game over add remaintime/15 to every step's rewards. to improve this round's training weight.
fix get target from states still using onehot decoder bug.

2022-12-03 03:58:19 +09:00

..

GAIL-Model

Add Gun State, fix PPO GAIL class bug

2022-10-23 23:38:07 +09:00

Pytorch

Add EndReward Broadcast function

2022-12-03 03:58:19 +09:00

Tensorflow

Parallel Environment Discrete PPO finish

2022-10-30 04:13:14 +09:00