Critic Guided Segmentation of Rewarding Objects in First-Person Views

07/20/2021
by   Andrew Melnik, et al.
0

This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://rebrand.ly/critic-guided-segmentation

READ FULL TEXT

page 2

page 3

research
07/06/2020

Scaling Imitation Learning in Minecraft

Imitation learning is a powerful family of techniques for learning senso...
research
06/05/2022

ARC – Actor Residual Critic for Adversarial Imitation Learning

Adversarial Imitation Learning (AIL) is a class of popular state-of-the-...
research
06/20/2018

Learning Neural Parsers with Deterministic Differentiable Imitation Learning

We address the problem of spatial segmentation of a 2D object in the con...
research
08/20/2020

Imitation Learning with Sinkhorn Distances

Imitation learning algorithms have been interpreted as variants of diver...
research
07/07/2020

Imitation Learning Approach for AI Driving Olympics Trained on Real-world and Simulation Data Simultaneously

In this paper, we describe our winning approach to solving the Lane Foll...
research
10/30/2021

Top1 Solution of QQ Browser 2021 Ai Algorithm Competition Track 1 : Multimodal Video Similarity

In this paper, we describe the solution to the QQ Browser 2021 Ai Algori...

Please sign up or login with your details

Forgot password? Click here to reset