165 citations · 950 across the 71 of their papers we have counts for
3 papers · 2 filters
Learning in Observable POMDPs, without Computationally Intractable Oracles
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Much of reinforcement learning theory is built on top of oracles that are computationally hard to implement. Specifically for learning near-optimal policies in Partially Observable…
Distilling Model Failures as Directions in Latent Space
Saachi Jain, Hannah Lawrence, Ankur Moitra +1
Existing methods for isolating hard subpopulations and spurious correlations in datasets often require human intervention. This can make these methods labor-intensive and dataset-s…
Planning in Observable POMDPs in Quasipolynomial Time
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Partially Observable Markov Decision Processes (POMDPs) are a natural and general model in reinforcement learning that take into account the agent's uncertainty about its current s…