Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding
Talk, INFORMS Healthcare Conference 2026, Raleigh, NC, USA
Talks and presentations
Integrating Causal DAGs in Deep RL: Activating Minimal Markovian States with Multi-Order Exposure
Talk, Amazon Scout RL Lunch Talk, New York, NY, USA
From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Performance
Talk, INFORMS Annual Meeting 2025, Atlanta, GA, USA