← authors · overview

• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
  2017 · 645 citations
• Deep Exploration via Bootstrapped DQN
  2016 · 468 citations
• Noisy Networks for Exploration
  2017 · 391 citations
• Learning to reinforcement learn
  2016 · 380 citations
• Model-Free Episodic Control
  2016 · 174 citations
• Agent57: Outperforming the Atari Human Benchmark
  2020 · 147 citations
• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
  2017 · 139 citations
• Neural Episodic Control
  2017 · 92 citations
• Never Give Up: Learning Directed Exploration Strategies
  2020 · 80 citations
• Generalization of Reinforcement Learners with Working and Episodic Memory
  2019 · 28 citations
• Fast deep reinforcement learning using online adjustments from the past
  2018 · 18 citations
• Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
  2021 · 12 citations
• CoBERL: Contrastive BERT for Reinforcement Learning
  2021 · 8 citations
• Retrieval-Augmented Reinforcement Learning
  2022 · 6 citations
• Emphatic Algorithms for Deep Reinforcement Learning
  2021 · 3 citations