On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning

• URL: http://arxiv.org/abs/2210.09256v1
• Date: Mon, 17 Oct 2022 16:59:48 GMT
• Title: On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning
• Authors: Philipp Becker, Gerhard Neumann
• Abstract summary: We show that RSSMs use a suboptimal inference scheme and that models trained using this inference overestimate the aleatoric uncertainty of the ground truth system. We propose an alternative approach building on well-understood components for modeling aleatoric and epistemic uncertainty, dubbed Variational Recurrent Kalman Network (VRKN) Our experiments show that using the VRKN instead of the RSSM improves performance in tasks where appropriately capturing aleatoric uncertainty is crucial.
• Score: 21.63642325390798
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Improved state space models, such as Recurrent State Space Models (RSSMs), are a key factor behind recent advances in model-based reinforcement learning (RL). Yet, despite their empirical success, many of the underlying design choices are not well understood. We show that RSSMs use a suboptimal inference scheme and that models trained using this inference overestimate the aleatoric uncertainty of the ground truth system. We find this overestimation implicitly regularizes RSSMs and allows them to succeed in model-based RL. We postulate that this implicit regularization fulfills the same functionality as explicitly modeling epistemic uncertainty, which is crucial for many other model-based RL approaches. Yet, overestimating aleatoric uncertainty can also impair performance in cases where accurately estimating it matters, e.g., when we have to deal with occlusions, missing observations, or fusing sensor modalities at different frequencies. Moreover, the implicit regularization is a side-effect of the inference scheme and not the result of a rigorous, principled formulation, which renders analyzing or improving RSSMs difficult. Thus, we propose an alternative approach building on well-understood components for modeling aleatoric and epistemic uncertainty, dubbed Variational Recurrent Kalman Network (VRKN). This approach uses Kalman updates for exact smoothing inference in a latent space and Monte Carlo Dropout to model epistemic uncertainty. Due to the Kalman updates, the VRKN can naturally handle missing observations or sensor fusion problems with varying numbers of observations per time step. Our experiments show that using the VRKN instead of the RSSM improves performance in tasks where appropriately capturing aleatoric uncertainty is crucial while matching it in the deterministic standard benchmarks.

Related papers

• Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability [59.758009422067]
  We propose a standalone Kalman filter layer that performs closed-form Gaussian inference in linear state-space models. Similar to efficient linear recurrent layers, the Kalman filter layer processes sequential data using a parallel scan. Experiments show that Kalman filter layers excel in problems where uncertainty reasoning is key for decision-making, outperforming other stateful models.
  arXiv  Detail & Related papers  (2024-09-25T11:22:29Z)
• Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation [50.920911532133154]
  The intrinsic ill-posedness and ordinal-sensitive nature of monocular depth estimation (MDE) models pose major challenges to the estimation of uncertainty degree. We propose to model the uncertainty of MDE models from the perspective of the inherent probability distributions. By simply introducing additional training regularization terms, our model, with surprisingly simple formations and without requiring extra modules or multiple inferences, can provide uncertainty estimations with state-of-the-art reliability.
  arXiv  Detail & Related papers  (2023-07-19T12:11:15Z)
• ALUM: Adversarial Data Uncertainty Modeling from Latent Model Uncertainty Compensation [25.67258563807856]
  We propose a novel method called ALUM to handle the model uncertainty and data uncertainty in a unified scheme. Our proposed ALUM is model-agnostic which can be easily implemented into any existing deep model with little extra overhead.
  arXiv  Detail & Related papers  (2023-03-29T17:24:12Z)
• Quantifying Model Uncertainty for Semantic Segmentation using Operators in the RKHS [20.348825818435767]
  We present a framework for high-resolution predictive uncertainty quantification of semantic segmentation models. We use a multi-moment functional definition of uncertainty associated with the model's feature space in the kernel reproducing the Hilbert space (RKHS) This leads to a significantly more accurate view of model uncertainty than conventional Bayesian methods.
  arXiv  Detail & Related papers  (2022-11-03T17:10:49Z)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty [68.00748155945047]
  Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. Our contribution is a novel abstraction-based controller method for continuous-state models with noise, uncertain parameters, and external disturbances.
  arXiv  Detail & Related papers  (2022-10-12T07:57:03Z)
• Learning Hidden Markov Models When the Locations of Missing Observations are Unknown [54.40592050737724]
  We consider the general problem of learning an HMM from data with unknown missing observation locations. We provide reconstruction algorithms that do not require any assumptions about the structure of the underlying chain. We show that under proper specifications one can reconstruct the process dynamics as well as if the missing observations positions were known.
  arXiv  Detail & Related papers  (2022-03-12T22:40:43Z)
• Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation [32.80370188601152]
  The paper proposes the Multi-Agent Adaptive Kalman Temporal Difference (MAK-TD) framework and its Successor Representation-based variant, referred to as the MAK-SR. The proposed MAK-TD/SR frameworks consider the continuous nature of the action-space that is associated with high dimensional multi-agent environments.
  arXiv  Detail & Related papers  (2021-12-30T18:21:53Z)
• MDN-VO: Estimating Visual Odometry with Confidence [34.8860186009308]
  Visual Odometry (VO) is used in many applications including robotics and autonomous systems. We propose a deep learning-based VO model to estimate 6-DoF poses, as well as a confidence model for these estimates. Our experiments show that the proposed model exceeds state-of-the-art performance in addition to detecting failure cases.
  arXiv  Detail & Related papers  (2021-12-23T19:26:04Z)
• Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models [84.18625250574853]
  We investigate the ability of KalmanNet, a proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. We show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the Kalman filter.
  arXiv  Detail & Related papers  (2021-10-10T08:52:18Z)
• Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder [59.69303945834122]
  We present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of time series. Our model parameterizes mean and variance for each time-stamp with flexible neural networks. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.
  arXiv  Detail & Related papers  (2021-02-02T06:15:15Z)

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.