Alert button
Picture for Jan Leike

Jan Leike

Alert button

Active Reinforcement Learning: Observing Rewards at a Cost

Nov 24, 2020
David Krueger, Jan Leike, Owain Evans, John Salvatier

Figure 1 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 2 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 3 for Active Reinforcement Learning: Observing Rewards at a Cost
Figure 4 for Active Reinforcement Learning: Observing Rewards at a Cost
Viaarxiv icon

Hidden Incentives for Auto-Induced Distributional Shift

Sep 19, 2020
David Krueger, Tegan Maharaj, Jan Leike

Figure 1 for Hidden Incentives for Auto-Induced Distributional Shift
Figure 2 for Hidden Incentives for Auto-Induced Distributional Shift
Figure 3 for Hidden Incentives for Auto-Induced Distributional Shift
Figure 4 for Hidden Incentives for Auto-Induced Distributional Shift
Viaarxiv icon

Quantifying Differences in Reward Functions

Jun 24, 2020
Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike

Figure 1 for Quantifying Differences in Reward Functions
Figure 2 for Quantifying Differences in Reward Functions
Figure 3 for Quantifying Differences in Reward Functions
Figure 4 for Quantifying Differences in Reward Functions
Viaarxiv icon

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
Viaarxiv icon

Learning Human Objectives by Evaluating Hypothetical Behavior

Dec 05, 2019
Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike

Figure 1 for Learning Human Objectives by Evaluating Hypothetical Behavior
Figure 2 for Learning Human Objectives by Evaluating Hypothetical Behavior
Figure 3 for Learning Human Objectives by Evaluating Hypothetical Behavior
Figure 4 for Learning Human Objectives by Evaluating Hypothetical Behavior
Viaarxiv icon

Scaling shared model governance via model splitting

Dec 14, 2018
Miljan Martic, Jan Leike, Andrew Trask, Matteo Hessel, Shane Legg, Pushmeet Kohli

Figure 1 for Scaling shared model governance via model splitting
Figure 2 for Scaling shared model governance via model splitting
Figure 3 for Scaling shared model governance via model splitting
Figure 4 for Scaling shared model governance via model splitting
Viaarxiv icon

Scalable agent alignment via reward modeling: a research direction

Nov 19, 2018
Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg

Figure 1 for Scalable agent alignment via reward modeling: a research direction
Figure 2 for Scalable agent alignment via reward modeling: a research direction
Figure 3 for Scalable agent alignment via reward modeling: a research direction
Figure 4 for Scalable agent alignment via reward modeling: a research direction
Viaarxiv icon

Reward learning from human preferences and demonstrations in Atari

Nov 15, 2018
Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei

Figure 1 for Reward learning from human preferences and demonstrations in Atari
Figure 2 for Reward learning from human preferences and demonstrations in Atari
Figure 3 for Reward learning from human preferences and demonstrations in Atari
Figure 4 for Reward learning from human preferences and demonstrations in Atari
Viaarxiv icon

Learning to Understand Goal Specifications by Modelling Reward

Oct 02, 2018
Dzmitry Bahdanau, Felix Hill, Jan Leike, Edward Hughes, Pushmeet Kohli, Edward Grefenstette

Figure 1 for Learning to Understand Goal Specifications by Modelling Reward
Figure 2 for Learning to Understand Goal Specifications by Modelling Reward
Figure 3 for Learning to Understand Goal Specifications by Modelling Reward
Figure 4 for Learning to Understand Goal Specifications by Modelling Reward
Viaarxiv icon