John Langford

収録論文 6本 ・ フィジカルAI/ロボット学習

※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。

論文

• Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
  2024/2/1
• PcLast: Discovering Plannable Continuous Latent States
  2023/11/1
• Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
  2022/11/1
• Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models
  2022/7/1
• Doubly Robust Policy Evaluation and Learning
  2011/3/1
• Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms
  2010/3/1