Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning

TL;DR

This paper introduces a prediction-based Markov Violation Score (MVS) to detect non-Markovian observations in reinforcement learning, helping distinguish sensor violations from other suboptimality sources.

Contribution

It proposes a novel, model-free score that quantifies non-Markovian structure in observations, validated across multiple environments and algorithms.

Findings

MVS correlates positively with noise intensity in high-dimensional tasks.

Under training noise, reward degradation aligns with increased MVS.

MVS effectively identifies partial observability and guides architecture choices.

Abstract

Reinforcement learning algorithms assume that observations satisfy the Markov property, yet real-world sensors frequently violate this assumption through correlated noise, latency, or partial observability. Standard performance metrics conflate Markov breakdowns with other sources of suboptimality, leaving practitioners without tools to detect such violations. This paper introduces a prediction-based Markov Violation Score (MVS) that quantifies non-Markovian structure in observation trajectories. A random forest first removes nonlinear Markov-compliant dynamics; ridge regression then tests whether historical observations reduce prediction error on the residuals beyond what the current observation provides. The resulting score is bounded in [0, 1] and requires no causal graph construction. Evaluation spans six environments (CartPole, Pendulum, Acrobot, HalfCheetah, Hopper, Walker2d), three algorithms (PPO, A2C, SAC), controlled AR(1) noise at six intensity levels, and 10 seeds per condition. In post-hoc detection, 7 of 16 environment-algorithm pairs, primarily high-dimensional locomotion tasks, show significant positive monotonicity between noise intensity and MVS (Spearman rho up to 0.78, confirmed under repeated-measures analysis); under training-time noise, 13 of 16 pairs exhibit statistically significant reward degradation. An inversion phenomenon is documented in low-dimensional environments where the random forest absorbs the noise signal, causing MVS to decrease as true violations grow, a failure mode analyzed in detail. A practical utility experiment demonstrates that MVS correctly identifies partial observability and guides architecture selection, fully recovering performance lost to non-Markovian observations. Source code to reproduce all results is available at https://github.com/NAVEENMN/Markovianes.