• Publications
  • Influence
Backplay: "Man muss immer umkehren"
TLDR
We explore a method to improve the sample efficiency when we have access to demonstrations. Expand
  • 30
  • 5
  • PDF
Multi-Agent Reinforcement Learning: A Report on Challenges and Approaches
TLDR
Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. Expand
  • 17
  • PDF
First-Order Preconditioning via Hypergradient Descent
TLDR
We introduce first-order preconditioning (FOP), a fast, scalable approach that generalizes previous work on hypergradient descent (Almeida et al., 1998; Maclaurin et al, 2015) to learn a preconditionsing matrix that only makes use of first- order information. Expand
  • 1
  • PDF
Variational Auto-Regressive Gaussian Processes for Continual Learning
TLDR
This paper proposes Variational Auto-Regressive Gaussian Process (VAR-GP), a principled Bayesian updating mechanism to incorporate new data for sequential tasks in the context of continual learning. Expand
  • 1
  • PDF