← Search

Gleb Shevchuk

2 accepted papers

2019

Learning Reward Functions by Integrating Human Demonstrations and Preferences

RSS 2019poster

Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which iteratively queries the user for her preferences between tra…

2019

Unsupervised Visuomotor Control through Distributional Planning Networks

RSS 2019poster

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where aspects of the environment needed to compute progress are no…

Cited by 48SourcePDFScholar