# Detecting Model Drifts in Non-Stationary Environment Using Edit Operation Measures

arXiv: https://arxiv.org/abs/2509.11367 · HTML: https://mlsanity.com/paper/2509.11367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 24 references that are in the map.
- First posted on arXiv 14 Sep 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 9 of 9)

- [Doubly Robust Off-policy Value Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1511.03722/) (2015)
- [A Survey of Reinforcement Learning Algorithms for Dynamically Varying Environments](https://mlsanity.com/paper/2005.10619/) (2020)
- [Offline RL Policies Should be Trained to be Adaptive](https://mlsanity.com/paper/2207.02200/) (2022)
- [Testing Stationarity and Change Point Detection in Reinforcement Learning](https://mlsanity.com/paper/2203.01707/) (2022)
- [Assessing the Impact of Distribution Shift on Reinforcement Learning Performance](https://mlsanity.com/paper/2402.03590/) (2024)
- [Online Reinforcement Learning in Non-Stationary Context-Driven Environments](https://mlsanity.com/paper/2302.02182/) (2023)
- [Sample Complexity Characterization for Linear Contextual MDPs](https://mlsanity.com/paper/2402.02700/) (2024)
- [Offline Reinforcement Learning from Datasets with Structured Non-Stationarity](https://mlsanity.com/paper/2405.14114/) (2024)
- [A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points](https://mlsanity.com/paper/2405.14214/) (2024)

## Abstract (arXiv)

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.