← authors · overview

• Hybrid Reward Architecture for Reinforcement Learning
  2017 · 188 citations
• Safe Policy Improvement with Baseline Bootstrapping
  2017 · 83 citations
• Counting to Explore and Generalize in Text-based Games
  2018 · 52 citations
• Multi-Advisor Reinforcement Learning
  2017 · 14 citations
• Budgeted Reinforcement Learning in Continuous State Space
  2019 · 9 citations
• Separation of Concerns in Reinforcement Learning
  2016 · 7 citations
• Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs
  2021 · 5 citations
• Think Before You Act: Decision Transformers with Working Memory
  2023 · 5 citations
• When does return-conditioned supervised learning work for offline reinforcement learning?
  2022 · 4 citations
• Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning