search

rail-berkeley / rlkit

Collection of reinforcement learning algorithms
MIT License
2.43k stars 547 forks source link

multi-GPU optimised implementations for running algorithms #148

Closed shivanimall closed 2 years ago

shivanimall commented 2 years ago

Hello,

Thank you for making this available! wondering if you have a variant repo that makes use of multi-GPU optimised implementations?

They have a paper and a repo which is 3 yrs old: https://github.com/astooke/accel_rl https://arxiv.org/pdf/1803.02811.pdf

anair13 commented 2 years ago

No, as far as I know there is no variant of rlkit that makes of multi-GPU optimized implementations.