Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier. We obtain the class conditional Gaussian distributions with respect to (low-and upper-level) features of the deep models under Gaussian discriminant analysis, which result in a confidence score based on the Mahalanobis distance. While most prior methods have been evaluated for detecting either out-of-distribution or adversarial samples, but not both, the proposed method achieves the state-of-the-art performances for both cases in our experiments. Moreover, we found that our proposed method is more robust in harsh cases, e.g., when the training dataset has noisy labels or small number of samples. Finally, we show that the proposed method enjoys broader usage by applying it to class-incremental learning: whenever out-of-distribution samples are detected, our classification rule can incorporate new classes well without further training deep models.

Unlike distance metric learning where the subsequent tasks utilizing the estimated distance metric is the usual focus, the proposal focuses on the estimated metric characterizing the geometry structure. Despite the illustrated taxi and MNIST examples, it is still open to finding more compelling applications that target the data space geometry. Interpreting mathematical concepts such as Riemannian metric and geodesic in the context of potential application (e.g., cognition and perception research where similarity measures are common) could be inspiring. Our proposal requires sufficiently dense data, which could be demanding, especially for high-dimensional data due to the curse of dimensionality. Dimensional reduction (e.g., manifold embedding as in the MNIST example) can substantially alleviate the curse of dimensionality, and the dense data requirement will more likely hold true.

Further analysis suggests a positive relationship (Spearman's r

We introduce a novel cyclic Markov decision process (MDP) framework for multi-step decision problems with heterogeneous stage-specific dynamics, transitions, and discount factors across the cycle. In this setting, offline learning is challenging: optimizing a policy at any stage shifts the state distributions of subsequent stages, propagating mismatch across the cycle. To address this, we propose a modular structural framework that decomposes the cyclic process into stage-wise sub-problems. While generally applicable, we instantiate this principle as CycleFQI, an extension of fitted Q-iteration enabling theoretical analysis and interpretation. It uses a vector of stage-specific Q-functions, tailored to each stage, to capture within-stage sequences and transitions between stages. This modular design enables partial control, allowing some stages to be optimized while others follow predefined policies. We establish finite-sample suboptimality error bounds and derive global convergence rates under Besov regularity, demonstrating that CycleFQI mitigates the curse of dimensionality compared to monolithic baselines. Additionally, we propose a sieve-based method for asymptotic inference of optimal policy values under a margin condition. Experiments on simulated and real-world Type 1 Diabetes data sets demonstrate CycleFQI's effectiveness.

OfflineRLisdeemed to be promising [16, 14] as online learning requires the agent to continuously interact with the environment, which howevermaybecostly,time-consuming, orevendangerous.

Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.

There are several GAN literature that adopts multiple discriminators [9-14]. Among them, GMAN [10] is closely related to our approach in the sense that it utilizes an ensemble predictionofdiscriminators.

Toovercome thelimitation, wepropose Latent Dynamics Mixture (LDM) that trains a reinforcement learning agent with imaginary tasks generated from mixtures of learned latent dynamics.