Michael Bowling

Toward Agents That Reason About Their Computation

BRIM: Block-wise Return Induction Method for Sequence Knowledge Distillation

Neural Bayesian Filtering

Generalization in Monitored Markov Decision Processes (Mon-MDPs)

Plasticity as the Mirror of Empowerment

Model-Based Exploration in Monitored Markov Decision Processes

Neural Bayesian Filtering

Assessing the Interpretability of Programmatic Policies using Large Language Models

Approximating Nash Equilibria in General-Sum Games via Meta-Learning

Meta-Learning in Self-Play Regret Minimization