Explainable reinforcement learning for broad-XAI: a conceptual framework and survey

• Published in: Neural computing & applications Vol. 35; no. 23; pp. 16893 - 16916
• Main Authors: Dazeley, Richard, Vamplew, Peter, Cruz, Francisco
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Communication; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Decision making; Image Processing and Computer Vision; Machine learning; Probability and Statistics in Computer Science; S.I.: Human-aligned Reinforcement Learning for Autonomous Agents and Robots; Special Issue on Human-aligned Reinforcement Learning for Autonomous Agents and Robots; Reinforcement learning (RL); Explainable artificial intelligence (XAI); Broad XAI; Explainable Reinforcement learning (XRL)
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-023-08423-1

Broad-XAI moves away from interpreting individual decisions based on a single datum and aims to provide integrated explanations from multiple machine learning algorithms into a coherent explanation of an agent’s behaviour that is aligned to the communication needs of the explainee. Reinforcement Learning (RL) methods, we propose, provide a potential backbone for the cognitive model required for the development of Broad-XAI. RL represents a suite of approaches that have had increasing success in solving a range of sequential decision-making problems. However, these algorithms operate as black-box problem solvers, where they obfuscate their decision-making policy through a complex array of values and functions. EXplainable RL (XRL) aims to develop techniques to extract concepts from the agent’s: perception of the environment; intrinsic/extrinsic motivations/beliefs; Q-values, goals and objectives. This paper aims to introduce the Causal XRL Framework (CXF), that unifies the current XRL research and uses RL as a backbone to the development of Broad-XAI. CXF is designed to incorporate many standard RL extensions and integrated with external ontologies and communication facilities so that the agent can answer questions that explain outcomes its decisions. This paper aims to: establish XRL as a distinct branch of XAI; introduce a conceptual framework for XRL; review existing approaches explaining agent behaviour; and identify opportunities for future research. Finally, this paper discusses how additional information can be extracted and ultimately integrated into models of communication, facilitating the development of Broad-XAI.