Brandon Amos

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

• Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback
  2024/10/1
• Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
  2022/10/1
• Theseus: A Library for Differentiable Nonlinear Optimization
  2022/7/1
• Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world
  2022/6/1
• Cross-Domain Imitation Learning via Optimal Transport
  2021/10/1
• On the model-based stochastic value gradient for continuous reinforcement learning
  2020/8/1
• Objective Mismatch in Model-based Reinforcement Learning
  2020/2/1
• Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
  2019/10/1
• The Differentiable Cross-Entropy Method
  2019/9/1
• Learning Awareness Models
  2018/4/1