New Approach in Human-AI Interaction by Reinforcement-Imitation Learning

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Reinforcement Learning (RL) provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment states and action spaces, as well as in the determination of rewards. Imitation Learning (IL) offers a promising solution for those challenges using a teacher. In IL, the learning process can take advantage of human-sourced assistance and/or control over the agent and environment. A human teacher and an agent learner are considered in this study. The teacher takes part in the agent’s training towards dealing with the environment, tackling a specific objective, and achieving a predefined goal. This paper proposes a novel approach combining IL with different types of RL methods, namely, state-action-reward-state-action (SARSA) and Asynchronous Advantage Actor–Critic Agents (A3C), to overcome the problems of both stand-alone systems. How to effectively leverage the teacher’s feedback—be it direct binary or indirect detailed—for the agent learner to learn sequential decision-making policies is addressed. The results of this study on various OpenAI-Gym environments show that this algorithmic method can be incorporated with different combinations, and significantly decreases both human endeavors and tedious exploration process.

This publication has 11 references indexed in Scilit: