03/05/2021

Planning from Pixels using Inverse Dynamics Models

Keiran Paster, Sheila McIlraith, Jimmy Ba

Keywords: model based reinforcement learning, deep learning, goal-conditioned reinforcement learning, deep reinforcement learning, multi-task learning

Abstract Paper Similar Papers

Abstract: Learning dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn models in a latent space by learning to predict sequences of future actions conditioned on task completion. These models track task-relevant environment dynamics over a distribution of tasks, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches.

 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ICLR 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 5:01 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 13:45 
 0
 0
 0
 0
 5:52 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 4:29 
 0
 0
 0
 0
 12:53 
 0
 0
 0
 0
 8:17 
 0
 0
 0
 0
 4:13 
 0
 0
 0
 0
 16:31 
 0
 0
 0
 0
 15:06 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:00 
 0
 0
 0
 0
 4:32 
 0
 0
 0
 0
 12:47 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 16:11 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 15:32 
 0
 0
 0
 0
 20:08 
 0
 0
 0
 0
 2:39 
 0
 0
 0
 0
 2:42 
 0
 1
 0
 0
 5:06 
 0
 0
 0
 0
 18:11 
 0
 0
 0
 0
 15:49 
 1
 0
 0
 0
 3:20 
 0
 0
 0
 0
 3:09 
 0
 0
 0
 0
 18:52 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 12:39 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 5:44 
 0
 0
 0
 0
 14:21 
 0
 0
 0
 0
 3:15 
 1
 1
 0
 0
 5:13 
 0
 0
 0
 1
 3:21