Improving Reinforcement Learning with Human Assistance: An Argument for Human Subject Studies with HIPPO Gym

TL;DR

This paper introduces HIPPO Gym, an open-source platform designed to facilitate human-assisted reinforcement learning research within OpenAI Gym environments, aiming to reduce data requirements and improve learning efficiency.

Contribution

The paper presents HIPPO Gym, a new framework that enables easy integration of human input into RL training, promoting research on human-guided learning methods.

Findings

HIPPO Gym simplifies human-RL research setup.

It supports various human teaching modalities.

It lowers barriers for investigating human assistance in RL.

Abstract

Reinforcement learning (RL) is a popular machine learning paradigm for game playing, robotics control, and other sequential decision tasks. However, RL agents often have long learning times with high data requirements because they begin by acting randomly. In order to better learn in complex tasks, this article argues that an external teacher can often significantly help the RL agent learn. OpenAI Gym is a common framework for RL research, including a large number of standard environments and agents, making RL research significantly more accessible. This article introduces our new open-source RL framework, the Human Input Parsing Platform for Openai Gym (HIPPO Gym), and the design decisions that went into its creation. The goal of this platform is to facilitate human-RL research, again lowering the bar so that more researchers can quickly investigate different ways that human teachers could assist RL agents, including learning from demonstrations, learning from feedback, or curriculum learning.