add Asynchronous Methods for Deep Reinforcement Learning

aikorea / awesome-rl

Reinforcement learning resources curated

http://aikorea.org/awesome-rl

8.74k stars 1.83k forks source link

add Asynchronous Methods for Deep Reinforcement Learning #10

Closed andrewliao11 closed 8 years ago

andrewliao11 commented 8 years ago

this work proposes a new method to solve the unstable deep RL network, asynchronous methods, with higher performance and shorter training time. this advantage offers practical benefits. it has some experiments on combining different basic algorithm, and all of them get a higher performance, which proves that it can be generally applied on many RL algorithm.

hshyunsookim commented 8 years ago

Link is broken and entry format is slightly different. I will fix these.