Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results

• URL: http://arxiv.org/abs/2107.04982v1
• Date: Sun, 11 Jul 2021 06:40:02 GMT
• Title: Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results
• Authors: Mohamad H Danesh and Alan Fern
• Abstract summary: We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution dynamics. This problem is particularly important in the context of deep RL, where learned controllers often overfit to the training environment. Our first contribution is to design a set of OODD benchmarks derived from common RL environments with varying types and intensities of OODD. Our second contribution is to design a strong OODD baseline approach based on recurrent implicit quantile networks (RIQNs), which monitors autoregressive prediction errors for OODD detection.
• Score: 21.054448068345348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of out-of-distribution dynamics (OODD) detection, which involves detecting when the dynamics of a temporal process change compared to the training-distribution dynamics. This is relevant to applications in control, reinforcement learning (RL), and multi-variate time-series, where changes to test time dynamics can impact the performance of learning controllers/predictors in unknown ways. This problem is particularly important in the context of deep RL, where learned controllers often overfit to the training environment. Currently, however, there is a lack of established OODD benchmarks for the types of environments commonly used in RL research. Our first contribution is to design a set of OODD benchmarks derived from common RL environments with varying types and intensities of OODD. Our second contribution is to design a strong OODD baseline approach based on recurrent implicit quantile networks (RIQNs), which monitors autoregressive prediction errors for OODD detection. Our final contribution is to evaluate the RIQN approach on the benchmarks to provide baseline results for future comparison.

Related papers

• Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation [2.0836728378106883]
  Training environments may not reflect real-life environments. Training systems are often equipped with out-of-distribution detectors that alert when a trained system encounters a state it does not recognize or in which it exhibits uncertainty.
  arXiv  Detail & Related papers  (2025-03-07T08:40:41Z)
• Advancing Out-of-Distribution Detection via Local Neuroplasticity [60.53625435889467]
  This paper presents a novel OOD detection method that leverages the unique local neuroplasticity property of Kolmogorov-Arnold Networks (KANs) Our method compares the activation patterns of a trained KAN against its untrained counterpart to detect OOD samples. We validate our approach on benchmarks from image and medical domains, demonstrating superior performance and robustness compared to state-of-the-art techniques.
  arXiv  Detail & Related papers  (2025-02-20T11:13:41Z)
• Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution [38.844580833635725]
  We present a training-time regularization technique to mitigate the bias and boost imbalanced OOD detectors across architecture designs. Our method translates into consistent improvements on the representative CIFAR10-LT, CIFAR100-LT, and ImageNet-LT benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T12:28:59Z)
• Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination [7.162274565861427]
  offline reinforcement learning in dynamic treatment regimes presents a mix of unprecedented opportunities and challenges. We argue for a reassessment of applying RL in dynamic treatment regimes citing concerns such as inconsistent and potentially inconclusive evaluation metrics. We demonstrate that the performance of RL algorithms can significantly vary with changes in evaluation metrics and Markov Decision Process (MDP) formulations.
  arXiv  Detail & Related papers  (2024-05-28T20:03:18Z)
• Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection [3.7384109981836158]
  We study the problem of out-of-distribution (OOD) detection in reinforcement learning (RL) We propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We find that DEXTER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-the-art OOD detectors and high-dimensional changepoint detectors adopted from statistics.
  arXiv  Detail & Related papers  (2024-04-10T15:39:49Z)
• DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization [58.704753031608625]
  Time series is one of the most challenging modalities in machine learning research. OOD detection and generalization on time series tend to suffer due to its non-stationary property. We propose DIVERSIFY, a framework for OOD detection and generalization on dynamic distributions of time series.
  arXiv  Detail & Related papers  (2023-08-04T12:27:11Z)
• Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study [71.84852429039881]
  Investigation focuses on the models' ability to handle a range of perturbations, such as sensor faults and noise. We test the generalization and transfer learning capabilities of these models by exposing them to out-of-distribution (OOD) samples.
  arXiv  Detail & Related papers  (2023-06-13T12:43:59Z)
• AUTO: Adaptive Outlier Optimization for Online Test-Time OOD Detection [81.49353397201887]
  Out-of-distribution (OOD) detection is crucial to deploying machine learning models in open-world applications. We introduce a novel paradigm called test-time OOD detection, which utilizes unlabeled online data directly at test time to improve OOD detection performance. We propose adaptive outlier optimization (AUTO), which consists of an in-out-aware filter, an ID memory bank, and a semantically-consistent objective.
  arXiv  Detail & Related papers  (2023-03-22T02:28:54Z)
• Energy-based Out-of-Distribution Detection for Graph Neural Networks [76.0242218180483]
  We propose a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe. GNNSafe achieves up to $17.0%$ AUROC improvement over state-of-the-arts and it could serve as simple yet strong baselines in such an under-developed area.
  arXiv  Detail & Related papers  (2023-02-06T16:38:43Z)
• Pseudo-OOD training for robust language models [78.15712542481859]
  OOD detection is a key component of a reliable machine-learning model for any industry-scale application. We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data. We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
  arXiv  Detail & Related papers  (2022-10-17T14:32:02Z)
• Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning [0.0]
  Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these solutions work well, but they fail when presented with out of distribution inputs. Out of distribution detection for RL is generally not well covered in the literature, and there is a lack of benchmarks for this task.
  arXiv  Detail & Related papers  (2021-12-05T22:21:11Z)
• Causal Inference Q-Network: Toward Resilient Reinforcement Learning [57.96312207429202]
  We consider a resilient DRL framework with observational interferences. Under this framework, we propose a causal inference based DRL algorithm called causal inference Q-network (CIQ) Our experimental results show that the proposed CIQ method could achieve higher performance and more resilience against observational interferences.
  arXiv  Detail & Related papers  (2021-02-18T23:50:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.