Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Laurent Orseau

Laurent Orseau

Policy-Guided Heuristic Search with Guarantees


Mar 21, 2021
Laurent Orseau, Levi H. S. Lelis

Figure 1 for Policy-Guided Heuristic Search with Guarantees
Figure 2 for Policy-Guided Heuristic Search with Guarantees
Figure 3 for Policy-Guided Heuristic Search with Guarantees
Figure 4 for Policy-Guided Heuristic Search with Guarantees

  Access Paper or Ask Questions

Training a First-Order Theorem Prover from Synthetic Data


Mar 05, 2021
Vlad Firoiu, Eser Aygun, Ankit Anand, Zafarali Ahmed, Xavier Glorot, Laurent Orseau, Lei Zhang, Doina Precup, Shibl Mourad

Figure 1 for Training a First-Order Theorem Prover from Synthetic Data
Figure 2 for Training a First-Order Theorem Prover from Synthetic Data
Figure 3 for Training a First-Order Theorem Prover from Synthetic Data
Figure 4 for Training a First-Order Theorem Prover from Synthetic Data

  Access Paper or Ask Questions

Avoiding Side Effects By Considering Future Tasks


Oct 15, 2020
Victoria Krakovna, Laurent Orseau, Richard Ngo, Miljan Martic, Shane Legg

Figure 1 for Avoiding Side Effects By Considering Future Tasks
Figure 2 for Avoiding Side Effects By Considering Future Tasks
Figure 3 for Avoiding Side Effects By Considering Future Tasks
Figure 4 for Avoiding Side Effects By Considering Future Tasks
* Published in NeurIPS 2020 
  Access Paper or Ask Questions

Logarithmic Pruning is All You Need


Jun 22, 2020
Laurent Orseau, Marcus Hutter, Omar Rivasplata

Figure 1 for Logarithmic Pruning is All You Need
Figure 2 for Logarithmic Pruning is All You Need

  Access Paper or Ask Questions

Learning to Prove from Synthetic Theorems


Jun 19, 2020
Eser Aygün, Zafarali Ahmed, Ankit Anand, Vlad Firoiu, Xavier Glorot, Laurent Orseau, Doina Precup, Shibl Mourad

Figure 1 for Learning to Prove from Synthetic Theorems
Figure 2 for Learning to Prove from Synthetic Theorems
Figure 3 for Learning to Prove from Synthetic Theorems
Figure 4 for Learning to Prove from Synthetic Theorems
* 17 pages, 6 figures, submitted to NeurIPS 2020 
  Access Paper or Ask Questions

Pitfalls of learning a reward function online


Apr 28, 2020
Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg

Figure 1 for Pitfalls of learning a reward function online
Figure 2 for Pitfalls of learning a reward function online
Figure 3 for Pitfalls of learning a reward function online
Figure 4 for Pitfalls of learning a reward function online

  Access Paper or Ask Questions

Iterative Budgeted Exponential Search


Jul 30, 2019
Malte Helmert, Tor Lattimore, Levi H. S. Lelis, Laurent Orseau, Nathan R. Sturtevant

Figure 1 for Iterative Budgeted Exponential Search
Figure 2 for Iterative Budgeted Exponential Search
Figure 3 for Iterative Budgeted Exponential Search
Figure 4 for Iterative Budgeted Exponential Search

  Access Paper or Ask Questions

Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees


Jun 07, 2019
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore

Figure 1 for Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
Figure 2 for Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
Figure 3 for Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
* This paper and another independent IJCAI 2019 submission have been merged into a single paper that subsumes both of them (Helmert et. al., 2019). This paper is placed here only for historical context. Please only cite the subsuming paper 
  Access Paper or Ask Questions

An investigation of model-free planning


Jan 11, 2019
Arthur Guez, Mehdi Mirza, Karol Gregor, Rishabh Kabra, Sébastien Racanière, Théophane Weber, David Raposo, Adam Santoro, Laurent Orseau, Tom Eccles, Greg Wayne, David Silver, Timothy Lillicrap

Figure 1 for An investigation of model-free planning
Figure 2 for An investigation of model-free planning
Figure 3 for An investigation of model-free planning
Figure 4 for An investigation of model-free planning

  Access Paper or Ask Questions

Soft-Bayes: Prod for Mixtures of Experts with Log-Loss


Jan 08, 2019
Laurent Orseau, Tor Lattimore, Shane Legg

* Algorithmic Learning Theory 2017 
  Access Paper or Ask Questions

Single-Agent Policy Tree Search With Guarantees


Nov 28, 2018
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore, Théophane Weber

Figure 1 for Single-Agent Policy Tree Search With Guarantees
Figure 2 for Single-Agent Policy Tree Search With Guarantees
Figure 3 for Single-Agent Policy Tree Search With Guarantees
* 32nd Conference on Neural Information Processing Systems (NIPS 2018), Montr\'eal, Canada 
  Access Paper or Ask Questions

Measuring and avoiding side effects using relative reachability


Jun 04, 2018
Victoria Krakovna, Laurent Orseau, Miljan Martic, Shane Legg

Figure 1 for Measuring and avoiding side effects using relative reachability
Figure 2 for Measuring and avoiding side effects using relative reachability
Figure 3 for Measuring and avoiding side effects using relative reachability
Figure 4 for Measuring and avoiding side effects using relative reachability

  Access Paper or Ask Questions

Agents and Devices: A Relative Definition of Agency


May 31, 2018
Laurent Orseau, Simon McGregor McGill, Shane Legg

Figure 1 for Agents and Devices: A Relative Definition of Agency
Figure 2 for Agents and Devices: A Relative Definition of Agency
Figure 3 for Agents and Devices: A Relative Definition of Agency
Figure 4 for Agents and Devices: A Relative Definition of Agency

  Access Paper or Ask Questions

AI Safety Gridworlds


Nov 28, 2017
Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg

Figure 1 for AI Safety Gridworlds
Figure 2 for AI Safety Gridworlds
Figure 3 for AI Safety Gridworlds
Figure 4 for AI Safety Gridworlds

  Access Paper or Ask Questions

Reinforcement Learning with a Corrupted Reward Channel


Aug 19, 2017
Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg

Figure 1 for Reinforcement Learning with a Corrupted Reward Channel
Figure 2 for Reinforcement Learning with a Corrupted Reward Channel
Figure 3 for Reinforcement Learning with a Corrupted Reward Channel
Figure 4 for Reinforcement Learning with a Corrupted Reward Channel
* A shorter version of this report was accepted to IJCAI 2017 AI and Autonomy track 
  Access Paper or Ask Questions

Thompson Sampling is Asymptotically Optimal in General Environments


Jun 03, 2016
Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter

* UAI 2016 
  Access Paper or Ask Questions