← authors · overview

• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
  2018 · 613 citations
• Deep reinforcement learning from human preferences
  2017 · 508 citations
• Noisy Networks for Exploration
  2017 · 391 citations
• Scalable agent alignment via reward modeling: a research direction
  2018 · 126 citations
• AI Safety Gridworlds
  2017 · 118 citations
• Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents
  2018 · 61 citations
• Reward learning from human preferences and demonstrations in Atari
  2018 · 39 citations
• Penalizing side effects using stepwise relative reachability
  2018 · 23 citations
• Quantifying Differences in Reward Functions
  2020 · 10 citations
• Learning Human Objectives by Evaluating Hypothetical Behavior
  2019 · 9 citations
• REALab: An Embedded Perspective on Tampering
  2020 · 3 citations
• Model-Free Risk-Sensitive Reinforcement Learning
  2021 · 2 citations
• Safe Deep RL in 3D Environments using Human Feedback
  2022 · 2 citations
• Your Policy Regularizer is Secretly an Adversary
  2022 · 2 citations