← authors · overview

• StarCraft II: A New Challenge for Reinforcement Learning
  2017 · 685 citations
• Rainbow: Combining Improvements in Deep Reinforcement Learning
  2017 · 428 citations
• Deep Q-learning from Demonstrations
  2017 · 307 citations
• Reinforcement Learning with Unsupervised Auxiliary Tasks
  2016 · 272 citations
• FeUdal Networks for Hierarchical Reinforcement Learning
  2017 · 252 citations
• Successor Features for Transfer in Reinforcement Learning
  2016 · 184 citations
• Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
  2019 · 57 citations
• Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
  2019 · 39 citations
• Universal Successor Features Approximators
  2018 · 24 citations
• Policy Evaluation Networks
  2020 · 14 citations
• Adapting Behaviour for Learning Progress
  2019 · 8 citations
• When should agents explore?
  2021 · 6 citations
• Vision-Language Models as a Source of Rewards
  2023 · 3 citations
• Scaling Goal-based Exploration via Pruning Proto-goals
  2023 · 1 citations
• Conditional Importance Sampling for Off-Policy Learning
  2019