Ondrej Biza

収録論文 15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

• When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning
  2026/5/1
• One-Shot Cross-Geometry Skill Transfer through Part Decomposition
  2026/4/1
• SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
  2026/3/1
• You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vector
  2026/3/1
• ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks
  2025/8/1
• On-Robot Reinforcement Learning with Goal-Contrastive Rewards
  2024/10/1
• ThinkGrasp: A Vision-Language System for Strategic Part Grasping in Clutter
  2024/7/1
• Imagination Policy: Using Generative Point Cloud Models for Learning Manipulation Policies
  2024/6/1
• Equivariant Offline Reinforcement Learning
  2024/6/1
• On Robot Grasp Learning Using Equivariant Models
  2023/6/1
• One-shot Imitation Learning via Interaction Warping
  2023/6/1
• Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks
  2022/7/1
• Sample Efficient Grasp Learning Using Equivariant Models
  2022/2/1
• Factored World Models for Zero-Shot Generalization in Robotic Manipulation
  2022/2/1
• Action Priors for Large Action Spaces in Robotics
  2021/1/1