Agent-Agnostic Human-in-the-Loop Reinforcement Learning

TL;DR

This paper introduces an agent-agnostic schema for human-in-the-loop reinforcement learning, enabling effective guidance without assuming specific agent architectures, and unifies existing teaching methods under this framework.

Contribution

The work proposes a general protocol program schema that encompasses various human-in-the-loop RL techniques, making them applicable across different agent architectures.

Findings

Unified framework for human-in-the-loop RL methods

Representation of existing approaches as special cases

Preliminary experiments demonstrate feasibility

Abstract

Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Reinforcement Learning without making strong assumptions about the inner workings of the agent. We show how to represent existing approaches such as action pruning, reward shaping, and training in simulation as special cases of our schema and conduct preliminary experiments on simple domains.