Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

06/27/2019
by   Santhosh K. Ramakrishnan, et al.
1

Standard computer vision systems assume access to intelligently captured inputs (e.g., photos from a human photographer), yet autonomously capturing good observations is a major challenge in itself. We address the problem of learning to look around: how can an agent learn to acquire informative visual observations? We propose a reinforcement learning solution, where the agent is rewarded for reducing its uncertainty about the unobserved portions of its environment. Specifically, the agent is trained to select a short sequence of glimpses after which it must infer the appearance of its full environment. To address the challenge of sparse rewards, we further introduce sidekick policy learning, which exploits the asymmetry in observability between training and test time. The proposed methods learn observation policies that not only perform the completion task for which they are trained, but also generalize to exhibit useful "look-around" behavior for a range of active perception tasks.

READ FULL TEXT

page 16

page 17

page 18

research
05/26/2020

Active Measure Reinforcement Learning for Observation Cost Minimization

Standard reinforcement learning (RL) algorithms assume that the observat...
research
09/23/2019

Where to Look Next: Unsupervised Active Visual Exploration on 360° Input

We address the problem of active visual exploration of large 360 inputs....
research
06/07/2023

Generalization Across Observation Shifts in Reinforcement Learning

Learning policies which are robust to changes in the environment are cri...
research
02/23/2021

Learning Sparse and Meaningful Representations Through Embodiment

How do humans acquire a meaningful understanding of the world with littl...
research
03/20/2023

Learning to Explore Informative Trajectories and Samples for Embodied Perception

We are witnessing significant progress on perception models, specificall...
research
04/20/2017

Learning to Acquire Information

We consider the problem of diagnosis where a set of simple observations ...
research
12/30/2021

Learning Agent State Online with Recurrent Generate-and-Test

Learning continually and online from a continuous stream of data is chal...

Please sign up or login with your details

Forgot password? Click here to reset