Detecting Model Drifts in Non-Stationary Environment Using Edit Operation Measures
Reinforcement learning (RL) agents typically assume stationary environment dynamics. Yet in real-world applications such as healthcare, robotics, and finance, transition probabilities or reward functions may evolve, leading to model drift. This paper proposes a novel framework to detect such drifts by analyzing the distributional changes in sequences of agent behavior. Specifically, we introduce a suite of edit operation-based measures to quantify deviations between state-action trajectories generated under stationary and perturbed conditions. Our experiments demonstrate that these measures can effectively distinguish drifted from non-drifted scenarios, even under varying levels of noise, providing a practical tool for drift detection in non-stationary RL environments.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Synthetic Non-stationary Data Streams for Recognition of the Unknown
The problem of data non-stationarity is commonly addressed in data stream processing. In a dynamic environment, methods should continuously be ready to analyze time-varying data -- hence, they should enable incremental t…
Open Set LearningKalman Filter Modifier for Neural Networks in Non-stationary Environments
Learning in a non-stationary environment is an inevitable problem when applying machine learning algorithm to real world environment. Learning new tasks without forgetting the previous knowledge is a challenge issue in m…
BIG-bench Machine LearningOn the Reliable Detection of Concept Drift from Streaming Unlabeled Data
Classifiers deployed in the real world operate in a dynamic environment, where the data distribution can change over time. These changes, referred to as concept drift, can cause the predictive performance of the classifi…
Change DetectionDrift DetectionUnderstanding Continual Learning Settings with Data Distribution Drift Analysis
Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this …
BIG-bench Machine LearningContinual LearningMulti-Source Transfer Learning for Non-Stationary Environments
In data stream mining, predictive models typically suffer drops in predictive performance due to concept drift. As enough data representing the new concept must be collected for the new concept to be well learnt, the pre…
Transfer Learning