Search Results for author: Jonathan N. Lee

Found 5 papers, 1 papers with code

Model Selection in Batch Policy Optimization

no code implementations23 Dec 2021 Jonathan N. Lee, George Tucker, Ofir Nachum, Bo Dai

We formalize the problem in the contextual bandit setting with linear model classes by identifying three sources of error that any model selection algorithm should optimally trade-off in order to be competitive: (1) approximation error, (2) statistical complexity, and (3) coverage.

Model Selection

Online Model Selection for Reinforcement Learning with Function Approximation

no code implementations19 Nov 2020 Jonathan N. Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill

Towards this end, we consider the problem of model selection in RL with function approximation, given a set of candidate RL algorithms with known regret guarantees.

Model Selection reinforcement-learning

Accelerated Message Passing for Entropy-Regularized MAP Inference

no code implementations ICML 2020 Jonathan N. Lee, Aldo Pacchiano, Peter Bartlett, Michael. I. Jordan

Maximum a posteriori (MAP) inference in discrete-valued Markov random fields is a fundamental problem in machine learning that involves identifying the most likely configuration of random variables given a distribution.

Dynamic Regret Convergence Analysis and an Adaptive Regularization Algorithm for On-Policy Robot Imitation Learning

1 code implementation6 Nov 2018 Jonathan N. Lee, Michael Laskey, Ajay Kumar Tanwani, Anil Aswani, Ken Goldberg

In this article, we reframe this result using dynamic regret theory from the field of online optimization and show that dynamic regret can be applied to any on-policy algorithm to analyze its convergence and optimality.

Imitation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.