Imitation Learning
التعلّم بالتقليد
تدريب وكيل بجعله يُقلّد عروض الخبراء، فيتعلّم سياسة من أزواج الحالة والفعل المُلاحَظة بدلاً من إشارة المكافأة.
Training an agent by having it mimic expert demonstrations, learning a policy from observed state-action pairs rather than from a reward signal.
Also translated asالتعلّم بالمحاكاة، التعلّم من العروض
First appears in this corpus in: Grandmaster Level in StarCraft II Using Multi-Agent Reinforcement Learning (2019)
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 ✦
- Grandmaster Level in StarCraft II Using Multi-Agent Reinforcement Learning2019in the sky ✦
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion2023in the sky ✦
- First Return, Then Explore2021in the sky ✦
- First Return, Then Explore2021in the sky ✦
- ReAct: Synergizing Reasoning and Acting in Language Models2023in the sky ✦
- RT-1: Robotics Transformer for Real-World Control at Scale2022in the sky ✦
- WebGPT: Browser-Assisted Question-Answering with Human Feedback2021in the sky ✦
- WebGPT: Browser-Assisted Question-Answering with Human Feedback2021in the sky ✦