Agent-Agnostic Human-in-the-Loop Reinforcement Learning
This work addresses the need for more flexible human-in-the-loop methods in reinforcement learning, but it is incremental as it generalizes existing approaches.
The paper tackles the problem of incorporating human expert advice into reinforcement learning without assuming specific agent representations, by proposing an agent-agnostic schema called protocol programs, and shows preliminary results on simple domains.
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.