search

IntelLabs / coach

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
https://intellabs.github.io/coach/
Apache License 2.0
2.32k stars 460 forks source link

Sync workers with global lock #361

Open kevinzou1982 opened 5 years ago

kevinzou1982 commented 5 years ago

compare to my last pull request 1, use global sync lock instand of lock_counter and release_counter in tensorflow. speed up counter access and prevent not zero problem. 2, fix a sync bug. Clipped_ppo_agent for example if int(batch.size / self.ap.network_wrappers['main'].batch_size) is different between each workers, some worker will be in acting phase and other workers will be block in wait_for_all_workers_barrier

gal-leibovich commented 5 years ago

is this replacing #347?

kevinzou1982 commented 5 years ago

Yes for my prj