DeepX-inc / machina

Control section: Deep Reinforcement Learning framework
MIT License
278 stars 45 forks source link

Faster sampling in random batch #179

Closed rarilurelo closed 5 years ago

rarilurelo commented 5 years ago

We take random batch by slicing permutation, but cost of generating permutation becomes high as length of Traj growing. We should implement a method which generates random batch faster.

rarilurelo commented 5 years ago

197