7

RecSys 2021 Challenge Workshop: Fairness-aware engagement prediction at scale on Twitter’s Home Timeline

The 2021 RecSys Challenge Dataset: Fairness is not optional

Composing Entropic Policies using Divergence Correction

Entropic Policy Composition with Generalized Policy Improvement and Successor Features

Transfer in Reinforcement Learning with Successor Features and Generalised Policy Improvement

Memory-based control with recurrent neural networks

1 Authors contributed equally.