# Extending Policy from One-Shot Learning through Coaching

## TL;DR

This paper introduces a one-shot learning framework for robots that combines self-evaluation and coaching via reinforcement learning to learn, correct, and adapt tasks from a single demonstration, making robot teaching more intuitive.

## Contribution

It presents a novel one-shot learning approach that integrates self-evaluation and human coaching to enable robots to learn and adapt tasks from a single demonstration.

## Key findings

- Successfully learned a scooping task from one demonstration.
- Reduced RL search space using resistive force theory.
- Extended task policy through human coaching for goal adaptation.

## Abstract

Humans generally teach their fellow collaborators to perform tasks through a small number of demonstrations. The learnt task is corrected or extended to meet specific task goals by means of coaching. Adopting a similar framework for teaching robots through demonstrations and coaching makes teaching tasks highly intuitive. Unlike traditional Learning from Demonstration (LfD) approaches which require multiple demonstrations, we present a one-shot learning from demonstration approach to learn tasks. The learnt task is corrected and generalized using two layers of evaluation/modification. First, the robot self-evaluates its performance and corrects the performance to be closer to the demonstrated task. Then, coaching is used as a means to extend the policy learnt to be adaptable to varying task goals. Both the self-evaluation and coaching are implemented using reinforcement learning (RL) methods. Coaching is achieved through human feedback on desired goal and action modification to generalize to specified task goals. The proposed approach is evaluated with a scooping task, by presenting a single demonstration. The self-evaluation framework aims to reduce the resistance to scooping in the media. To reduce the search space for RL, we bootstrap the search using least resistance path obtained using resistive force theory. Coaching is used to generalize the learnt task policy to transfer the desired quantity of material. Thus, the proposed method provides a framework for learning tasks from one demonstration and generalizing it using human feedback through coaching.