Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

TL;DR

HuGE introduces a method for reinforcement learning that effectively uses low-quality, asynchronous human feedback to guide exploration and policy learning without requiring detailed reward functions, applicable in simulation and real-world robotics.

Contribution

The paper presents HuGE, a novel approach that leverages noisy, asynchronous human feedback to guide exploration and learn policies without handcrafted rewards.

Findings

HuGE successfully learns complex robotic tasks in simulation.

It operates effectively with sporadic, non-expert human feedback.

The method scales to real-world robots with minimal human input.

Abstract

Exploration and reward specification are fundamental and intertwined challenges for reinforcement learning. Solving sequential decision-making tasks requiring expansive exploration requires either careful design of reward functions or the use of novelty-seeking exploration bonuses. Human supervisors can provide effective guidance in the loop to direct the exploration process, but prior methods to leverage this guidance require constant synchronous high-quality human feedback, which is expensive and impractical to obtain. In this work, we present a technique called Human Guided Exploration (HuGE), which uses low-quality feedback from non-expert users that may be sporadic, asynchronous, and noisy. HuGE guides exploration for reinforcement learning not only in simulation but also in the real world, all without meticulous reward specification. The key concept involves bifurcating human feedback and policy learning: human feedback steers exploration, while self-supervised learning from the exploration data yields unbiased policies. This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses. HuGE is able to learn a variety of challenging multi-stage robotic navigation and manipulation tasks in simulation using crowdsourced feedback from non-expert users. Moreover, this paradigm can be scaled to learning directly on real-world robots, using occasional, asynchronous feedback from human supervisors.