mwhittaker / deeprl_project

Deep RL Final Project
1 stars 1 forks source link

Long term #6

Open vlad17 opened 7 years ago

vlad17 commented 7 years ago

Ladder nets instead of AE; consider attention mechanisms here. Ladder impls (paper):

Use the model f that we learned (model based-rl algs, can we apply to MPC? -> need to find industrial-strength MPC algo).

other tasks (not just pong): consider https://piazza.com/class/j6l2zpz570w7jq?cid=262