search

deeplearninc / relaax

Reinforcement Learning framework to facilitate development and use of scalable RL algorithms and applications
Other
62 stars 11 forks source link

Distributed FuN #43

Open 4SkyNet opened 7 years ago

4SkyNet commented 7 years ago

TODO: Distributed version of FuN - FeUdal Networks for Hierarchical Reinforcement Learning (original paper)

4SkyNet commented 7 years ago

Test new A3C-LSTM with 8 threads as underlaid based for perception and worker (gym's Pong environment) new-a3c-lstm

4SkyNet commented 7 years ago

fun

4SkyNet commented 7 years ago

Test (one more time) vanilla A3C-LSTM with 8 threads & 20 steps (last gym's PongDeterministic-v4) 315 steps/sec on c4.xlarge with only 4 vCPU PS> gradient clipping added to compare with previous one (resized one RGB frame as input) my_pong_baseline