<ul><li>The AI system EXPLORER utilizes a Symbolic Policy Learner to learn policy actions in a text-based environment.</li><li>EXPLORER collects state, action, and reward pairs while exploring the text-based environment using ILP algorithms.</li><li>The ILP algorithm requires the goal, predicate list, and examples to learn the rules in the text-based environment.</li><li>EXPLORER utilizes exception learning to handle scenarios where information is missing, adding flexibility to the learned rules.</li></ul>

AI That Learns and Unlearns: The Exceptionally Smart EXPLORER

Discover more