Behavioral Cloning
الاستنساخ السلوكي
أسلوب تعلم خاضع للإشراف في التعلم بالتقليد يُدرَّب فيه النموذج على التنبؤ مباشرةً بأفعال الخبير من الملاحظات. يستخدم RT-2 الاستنساخ السلوكي بدلاً من التعلم المعزز.
A supervised learning approach to imitation learning where the policy is trained to directly predict expert actions from observations. RT-2 uses behavioral cloning rather than reinforcement learning.
Also translated asالتقليد السلوكي، النسخ السلوكي الخاضع للإشراف
First appears in this corpus in: Decision Transformer: Reinforcement Learning via Sequence Modeling (2021)
Appears in these papers
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023in the sky ✦
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware2023in the sky ✦
- Decision Transformer: Reinforcement Learning via Sequence Modeling2021in the sky ✦
- Decision Transformer: Reinforcement Learning via Sequence Modeling2021in the sky ✦
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023in the sky ✦
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023in the sky ✦
- A Generalist Agent2022in the sky ✦
- A Generalist Agent2022in the sky ✦
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models2024in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022in the sky ✦
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances2022in the sky ✦