Unverified50% confidenceFactExact time
When a neural network trained offline is deployed to a closed-loop control system, its actions change the system's state distribution, causing the data distribution at actual runtime to deviate from the offline data distribution at training time, that is, distribution shift.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn multi-agent systems, if training signals are mixed with artificial interactions produced by other agents pursuing their own metric maximization, the feedback distribution will undergo systematic drift, which is related to the data distribution shift problem in machine learning.78% similarUnverifiedWhen the distribution of online data deviates from the training data, model performance degrades (data drift and model decay), requiring retraining to be triggered.77% similarVerifiedBehavioral cloning suffers from the distribution shift problem: during training the policy only encounters the state distribution covered by expert trajectories, and during deployment the accumulation of small deviations causes the actual state distribution visited to gradually diverge from the training distribution.76% similarUnverified经验回放将交互经验存入固定大小缓冲区并随机采样小批量训练，打破连续经验的时间相关性，使神经网络训练更稳定74% similarUnverifiedThe loss surface of multi-layer neural networks is filled with local minima and saddle points, and training requires optimization techniques such as momentum, adaptive learning rates, regularization, and batch normalization.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1042121API
curl https://kongchang.com/api/v1/knowledge/claims/1042121MCP
get_claim(id=1042121)