Search Results for author:
Found 3 papers, 0 papers with code
Importance-Weighted Offline Learning Done Right
These improvements are made possible by the observation that the upper and lower tails importance-weighted estimators behave very differently from each other, and their careful control can massively improve on previous results that were all based on symmetric two-sided concentration inequalities.
Offline Primal-Dual Reinforcement Learning for Linear MDPs
Offline Reinforcement Learning (RL) aims to learn a near-optimal policy from a fixed dataset of transitions collected by another policy.
Online Learning with Off-Policy Feedback
We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
