@article{Madumal_2020, title={Explainable Agency in Reinforcement Learning Agents}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/7134}, DOI={10.1609/aaai.v34i10.7134}, abstractNote={<p>This thesis explores how reinforcement learning (RL) agents can provide explanations for their actions and behaviours. As humans, we build <em>causal models</em> to encode cause-effect relations of events and use these to explain <em>why</em> events happen. Taking inspiration from cognitive psychology and social science literature, I build <em>causal</em> explanation models and explanation dialogue models for RL agents. By mimicking human-like explanation models, these agents can provide explanations that are <em>natural</em> and <em>intuitive</em> to humans.</p>}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Madumal, Prashan}, year={2020}, month={Apr.}, pages={13724-13725} }