4.3k citations · 7.2k across the 45 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 117 cited
AI Safety Gridworlds
Jan Leike, Miljan Martic, Victoria Krakovna +5
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side…
stat.ML2017★ 499 cited
Deep reinforcement learning from human preferences
Paul Christiano, Jan Leike, Tom B. Brown +3
For sophisticated reinforcement learning (RL) systems to interact usefully with real-world environments, we need to communicate complex goals to these systems. In this work, we exp…