Erdem Bıyık

収録論文 39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

• Causally Robust Reward Learning from Reason-Augmented Preference Feedback
  2026/3/1
• Judgelight: Trajectory-Level Post-Optimization for Multi-Agent Path Finding via Closed-Subwalk Collapsing
  2026/1/1
• AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
  2025/11/1
• Actor-Free Continuous Control via Structurally Maximizable Q-Functions
  2025/10/1
• When a Robot is More Capable than a Human: Learning from Constrained Demonstrators
  2025/10/1
• PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies
  2025/9/1
• GABRIL: Gaze-Based Regularization for Mitigating Causal Confusion in Imitation Learning
  2025/7/1
• HAND Me the Data: Fast Robot Adaptation via Hand Path Retrieval
  2025/5/1
• IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories via Vision-Language Models
  2025/3/1
• Multi-Agent Inverse Q-Learning from Demonstrations
  2025/3/1
• RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks
  2025/3/1
• MILE: Model-based Intervention Learning
  2025/2/1
• NaVILA: Legged Robot Vision-Language-Action Model for Navigation
  2024/12/1
• Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions
  2024/10/1
• Trajectory Improvement and Reward Learning from Comparative Language Feedback
  2024/10/1
• A Generalized Acquisition Function for Preference-based Reward Learning
  2024/3/1
• ViSaRL: Visual Reinforcement Learning Guided by Human Saliency
  2024/3/1
• Batch Active Learning of Reward Functions from Human Preferences
  2024/2/1
• RoboCLIP: One Demonstration is Enough to Learn Robot Policies
  2023/10/1
• Active Reward Learning from Online Preferences
  2023/2/1
• Learning Preferences for Interactive Autonomy
  2022/10/1
• Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction
  2022/3/1
• Partner-Aware Algorithms in Decentralized Cooperative Bandit Teams
  2021/10/1
• Learning Reward Functions from Scale Feedback
  2021/10/1
• Learning Multimodal Rewards from Rankings
  2021/9/1
• APReL: A Library for Active Preference-based Reward Learning Algorithms
  2021/8/1
• Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy
  2021/6/1
• Preference-based Learning of Reward Function Features
  2021/3/1
• ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes
  2020/11/1
• Multi-Agent Safe Planning with Gaussian Processes
  2020/8/1
• Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving
  2020/7/1
• Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences
  2020/6/1
• Active Preference-Based Gaussian Process Regression for Reward Learning
  2020/5/1
• Asking Easy Questions: A User-Friendly Approach to Active Reward Learning
  2019/10/1
• Learning How to Dynamically Route Autonomous Vehicles on Shared Roads
  2019/9/1
• Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models
  2019/4/1
• The Green Choice: Learning and Influencing Human Decisions on Shared Roads
  2019/4/1
• Altruistic Autonomy: Beating Congestion on Shared Roads
  2018/10/1
• Batch Active Preference-Based Learning of Reward Functions
  2018/10/1