Verified75% confidenceFactExact time
Behavioral Cloning, as the most fundamental imitation learning method, suffers from the compounding error problem, where models tend to produce cascading failures on states outside the training distribution.
3
Sources
75%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified分布漂移是行为克隆的核心缺陷，因训练数据全部来自正确操作轨迹，模型未见过犯错后如何恢复的场景78% similarUnverifiedBecause the Tic-Tac-Toe training data covers all possible states, the model's learning task degenerates into a memorization task with no out-of-distribution issues, and the compounding error problem of behavioral cloning naturally dissolves.78% similarUnverifiedAutoregressive models suffer from the exposure bias problem, whereby the model sees real prefixes during training but faces self-generated erroneous prefixes during inference, causing errors to accumulate progressively.76% similarUnverified自回归生成系统训练采用Teacher Forcing策略，推理阶段切换为自回归模式后产生分布偏移导致误差累积放大73% similarUnverified蒸馏训练范式导致开源模型学习到经过高度过滤、几乎不包含失败和纠错过程的数据分布，使模型形成不愿自我纠正的性格73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/530926API
curl https://kongchang.com/api/v1/knowledge/claims/530926MCP
get_claim(id=530926)