Analogical reasoning is a fundamental capacity of human cognition that a...
Recently, the Successor Features and Generalized Policy Improvement (SF ...
We advance a novel explanation of similarity-based interference effects ...
Learning to flexibly follow task instructions in dynamic environments po...
First-person object-interaction tasks in high-fidelity, 3D, simulated
en...
The exploreexploit dilemma is one of the central challenges in Reinforce...