search

mwhittaker / deeprl_project

Deep RL Final Project
1 stars 1 forks source link

Jointly learned dynamics/encoding for PPO #32

Open vlad17 opened 6 years ago

vlad17 commented 6 years ago

Apply the jointly learned dynamic/encoder encoding from #26 to the encoder used in #31 and see if PPO improves

Blocked on #26 #31 Deliverables: learning curve for PPO under new state