65 citations · 198 across the 14 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.LG2022
When is Realizability Sufficient for Off-Policy Reinforcement Learning?
Andrea Zanette
Model-free algorithms for reinforcement learning typically require a condition called Bellman completeness in order to successfully operate off-policy with function approximation,…
cs.LG2022
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning
Andrea Zanette, Martin J. Wainwright
The -learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction wit…
cs.LG2022
Bellman Residual Orthogonalization for Offline Reinforcement Learning
Andrea Zanette, Martin J. Wainwright
We propose and analyze a reinforcement learning principle that approximates the Bellman equations by enforcing their validity only along an user-defined space of test functions. Fo…