Learning Reward Functions for Robotic Manipulation by Observing Humans

no code implementations • 16 Nov 2022 • Minttu Alakuijala, Gabriel Dulac-Arnold, Julien Mairal, Jean Ponce, Cordelia Schmid

Unlike prior work on leveraging human videos to teach robots, our method, Human Offline Learned Distances (HOLD) requires neither a priori data from the robot environment, nor a set of task-specific human demonstrations, nor a predefined notion of correspondence across morphologies, yet it is able to accelerate training of several manipulation tasks on a simulated robot arm compared to using only a sparse reward obtained from task completion.

Contrastive Learning

Residual Reinforcement Learning from Demonstrations

no code implementations • 15 Jun 2021 • Minttu Alakuijala, Gabriel Dulac-Arnold, Julien Mairal, Jean Ponce, Cordelia Schmid

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal.

reinforcement-learning Reinforcement Learning (RL)