Regularizing Trajectory Optimization with Denoising Autoencoders


Rinu Boney*, Norman Di Palo*, Mathias Berglund, Alexander Ilin, Juho Kannala, Antti Rasmus, Harri Valpola.

(*equal contribution, rest in alphabetical order)

Companion website for the paper presented at NeurIPS 2019.


Video showcasing the learning phase of CartPole, HalfCheetah and Ant using our method.

final_5d3186615247b20014f27b95_800143.mp4