← 返回课程
JHU Hands-on Robot Learning Fall 2026 · 单元 4官方资料已接入
Imitation learning and action chunking
- 日期
- 2026-09-24
- 课程资料
- 1 项
- 内容产物
- 0 项
视频待接入官方资源发布后会自动出现在这里
课程简介
Policies, states, observations, and Markov decision processes; Behavioral cloning; Covariate shift and compounding errors; Recovery data, DART, and DAgger; Policy evaluation and causal confusion; Action chunking and observation, prediction, and execution horizons; ACT architecture, training, and inference; Practical policy training and controller consistency; Temporal ensembling; and Tradeoffs in chunk length and policy context.
课程笔记
本单元的课程笔记尚未生成。
Blog 解读
本单元的Blog 解读尚未生成。
中文逐字稿
本单元的中文逐字稿尚未生成。
英文逐字稿
本单元的英文逐字稿尚未生成。