Henry Williams

収録論文 10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

• 反復による強化：強化学習における即時エピソード反復によるサンプル効率の向上
  強化学習2026/8/18

  成功したエピソードの行動系列を即座に繰り返す新しいメカニズム「Instant Episode Repetition (IER)」を提案し、SACやTD3に統合してサンプル効率を向上させた。

• Accelerating Real-World Overtaking in F1TENTH Racing Employing Reinforcement Learning Methods
  2025/10/1
• Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method
  2025/1/1
• Benchmarking Reinforcement Learning Methods for Dexterous Robotic Manipulation with a Three-Fingered Gripper
  2024/8/1
• Deep Reinforcement Learning for Local Path Following of an Autonomous Formula SAE Vehicle
  2024/1/1
• Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car
  2023/8/1
• Seeing the Fruit for the Leaves: Robotically Mapping Apple Fruitlets in a Commercial Orchard
  2023/8/1
• Seeing the Fruit for the Leaves: Towards Automated Apple Fruitlet Thinning
  2023/2/1
• Kiwifruit detection in challenging conditions
  2020/6/1
• Deep Neural Network Based Real-time Kiwi Fruit Flower Detection in an Orchard Environment
  2020/6/1