← authors · overview

• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
  2017 · 341 citations
• Lipschitz Continuity in Model-based Reinforcement Learning
  2018 · 37 citations
• Combating the Compounding-Error Problem with a Multi-step Model
  2019 · 27 citations
• An Alternative Softmax Operator for Reinforcement Learning
  2016 · 26 citations
• Mean Actor Critic
  2017 · 16 citations
• Sample-efficient Deep Reinforcement Learning for Dialog Control
  2016 · 10 citations
• Equivalence Between Wasserstein and Value-Aware Loss for Model-based Reinforcement Learning
  2018 · 9 citations
• Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
  2018 · 6 citations
• Continuous Doubly Constrained Batch Reinforcement Learning
  2021 · 6 citations