Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning

TL;DR

This paper introduces a subgoal-based reward shaping method that leverages human knowledge of subgoals to significantly improve learning efficiency in reinforcement learning across various domains.

Contribution

The authors extend potential-based reward shaping to incorporate human-understandable subgoals, making it easier for humans to enhance reinforcement learning performance.

Findings

Our method outperforms baseline and other subgoal methods in learning efficiency.

Experiments conducted in three different domains validate the effectiveness of the proposed approach.

Human-provided subgoals significantly accelerate reinforcement learning processes.

Abstract

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge in real environments. Many studies have incorporated human knowledge into reinforcement Learning. Though human knowledge on trajectories is often used, a human could be asked to control an AI agent, which can be difficult. Knowledge on subgoals may lessen this requirement because humans need only to consider a few representative states on an optimal trajectory in their minds. The essential factor for learning efficiency is rewards. Potential-based reward shaping is a basic method for enriching rewards. However, it is often difficult to incorporate subgoals for accelerating learning over potential-based reward shaping. This is because the appropriate potentials are not intuitive for humans. We extend potential-based reward shaping and propose a subgoal-based reward shaping. The method makes it easier for human trainers to share their knowledge of subgoals. To evaluate our method, we obtained a subgoal series from participants and conducted experiments in three domains, four-rooms(discrete states and discrete actions), pinball(continuous and discrete), and picking(both continuous). We compared our method with a baseline reinforcement learning algorithm and other subgoal-based methods, including random subgoal and naive subgoal-based reward shaping. As a result, we found out that our reward shaping outperformed all other methods in learning efficiency.