Explainable Agency in Reinforcement Learning Agents

Authors

  • Prashan Madumal The University of Melbourne

DOI:

https://doi.org/10.1609/aaai.v34i10.7134

Abstract

This thesis explores how reinforcement learning (RL) agents can provide explanations for their actions and behaviours. As humans, we build causal models to encode cause-effect relations of events and use these to explain why events happen. Taking inspiration from cognitive psychology and social science literature, I build causal explanation models and explanation dialogue models for RL agents. By mimicking human-like explanation models, these agents can provide explanations that are natural and intuitive to humans.

Downloads

Published

2020-04-03

How to Cite

Madumal, P. (2020). Explainable Agency in Reinforcement Learning Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 34(10), 13724-13725. https://doi.org/10.1609/aaai.v34i10.7134

Issue

Section

Doctoral Consortium Track