A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review

TL;DR

This paper reviews externally-influenced reinforcement learning methods, proposing a conceptual framework and taxonomy to facilitate collaboration and comparison among approaches that incorporate external information to enhance agent learning.

Contribution

It introduces a novel taxonomy for assisted reinforcement learning, clarifying relationships and processes involving external information sources and their influence on agents.

Findings

Proposes a comprehensive taxonomy for assisted reinforcement learning.

Identifies key streams using external information, such as transfer and demonstration learning.

Highlights future research directions in externally-influenced RL.

Abstract

A long-term goal of reinforcement learning agents is to be able to perform tasks in complex real-world scenarios. The use of external information is one way of scaling agents to more complex problems. However, there is a general lack of collaboration or interoperability between different approaches using external information. In this work, while reviewing externally-influenced methods, we propose a conceptual framework and taxonomy for assisted reinforcement learning, aimed at fostering collaboration by classifying and comparing various methods that use external information in the learning process. The proposed taxonomy details the relationship between the external information source and the learner agent, highlighting the process of information decomposition, structure, retention, and how it can be used to influence agent learning. As well as reviewing state-of-the-art methods, we identify current streams of reinforcement learning that use external information in order to improve the agent's performance and its decision-making process. These include heuristic reinforcement learning, interactive reinforcement learning, learning from demonstration, transfer learning, and learning from multiple sources, among others. These streams of reinforcement learning operate with the shared objective of scaffolding the learner agent. Lastly, we discuss further possibilities for future work in the field of assisted reinforcement learning systems.