Yannis Flet-Berliac
Home
Publications
Talks
Software
Teaching
CV
cs.stanford.edu/~yfletberliac
Page not found
Perhaps you were looking for one of these?
Publications
Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets
Model-based Offline Reinforcement Learning with Local Misspecification
Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data
Offline Policy Optimization with Eligible Actions
SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics
Talks
Efficient Actor-Critics under the Prism of Variance
Adversarially Guided Actor-Critic
Learning Value Functions using Residual Variance in Deep Policy Gradients
Oral & Panel Discussion: Do we control the algorithms we create?
Improving Policy Gradient Updates with MERL and SAUNA
Cite
×