← authors · overview

• StarCraft II: A New Challenge for Reinforcement Learning
  2017 · 685 citations
• Distributed Prioritized Experience Replay
  2018 · 415 citations
• Deep Q-learning from Demonstrations
  2017 · 307 citations
• Distral: Robust Multitask Reinforcement Learning
  2017 · 183 citations
• Observe and Look Further: Achieving Consistent Performance on Atari
  2018 · 87 citations
• Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
  2019 · 57 citations
• Universal Successor Features Approximators
  2018 · 24 citations
• Vision-Language Models as a Source of Rewards
  2023 · 3 citations
• Rethinking Thinking Tokens: LLMs as Improvement Operators
  2025
• The Value-Improvement Path: Towards Better Representations for Reinforcement Learning
  2020
• The Phenomenon of Policy Churn
  2022