Timezone: »

 
Poster
Regularizing Trajectory Optimization with Denoising Autoencoders
Rinu Boney · Norman Di Palo · Mathias Berglund · Alexander Ilin · Juho Kannala · Antti Rasmus · Harri Valpola

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #190
in Reinforcement Learning and Planning -- Model-Based RL »

Trajectory optimization using a learned model of the environment is one of the core elements of model-based reinforcement learning. This procedure often suffers from exploiting inaccuracies of the learned model. We propose to regularize trajectory optimization by means of a denoising autoencoder that is trained on the same trajectories as the model of the environment. We show that the proposed regularization leads to improved planning with both gradient-based and gradient-free optimizers. We also demonstrate that using regularized trajectory optimization leads to rapid initial learning in a set of popular motor control tasks, which suggests that the proposed approach can be a useful tool for improving sample efficiency.

Keywords: Reinforcement Learning and Planning · Reinforcement Learning · Reinforcement Learning and Planning -> Model-Based RL; Reinforcement Learning and Planning
[ Paper]  [ Poster] 

Author Information

Rinu Boney (Aalto University)
Norman Di Palo (-)
Mathias Berglund (Curious AI)
Alexander Ilin (Aalto University)
Juho Kannala (Aalto University)
Antti Rasmus (The Curious AI Company)
Harri Valpola (Curious AI)

More from the Same Authors