Verified65% confidenceFactExact time
Behavioral cloning simplifies the problem to supervised learning, but suffers from distribution shift, where differences between the state distributions at training time and execution time lead to error accumulation.
3
Sources
65%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
VerifiedBehavioral cloning suffers from the distribution shift problem, where the model tends to make errors and accumulate mistakes on states outside the training distribution, a phenomenon referred to as compounding error in the robotics control field.85% similarUnverified行为克隆（BC）存在复合误差与分布偏移问题，智能体偏离训练分布后预测误差会指数级累积81% similarVerified仅用成功轨迹训练的模型往往存在分布外泛化的严重缺陷，遇到工具返回错误时便丧失纠偏能力78% similarUnverifiedDuring cross-domain fine-tuning, an excessively large learning rate will destroy pre-trained weights, while an excessively small one will result in almost no learning, requiring a careful trade-off.78% similarUnverifiedBehavioral Cloning is susceptible to the compounding error problem, whereby minor deviations during policy execution accumulate continuously, causing the trajectory to deviate from the demonstration distribution.78% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/558057API
curl https://kongchang.com/api/v1/knowledge/claims/558057MCP
get_claim(id=558057)