Partially observable environments present an important open challenge in the domain of sequential control learning with delayed rewards. Despite numerous attempts during the two last decades, the majority of reinforcement learning algorithms and associated approximate models, applied to this context, still assume Marko…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “end-to-end control”
End-to-end algorithm for controlling bilinear systems with probabilistic noise.
problem Controlling bilinear systems with noisy data.
method Proposes an end-to-end algorithm using statistical learning theory and robust controller design.
result Derived finite sample identification error bounds and structurally suitable for control.
Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable obje…
NOVAS: Non-convex Optimization via Adaptive Stochastic Search for End-to-End Learning and Controlcs.LG
NOVAS uses adaptive stochastic search for non-convex optimization in deep networks.
problem Non-convex optimization challenges in deep neural networks.
method Adaptive stochastic search for non-convex optimization.
result NOVAS outperforms existing alternatives in a structured prediction task.
DeepRacing uses neural networks to predict trajectories for autonomous racing in video games.
problem Training algorithms for high-speed autonomous racing in realistic environments.
method Developed a virtual testbed using F1 video games, trained neural networks to predict trajectories and control commands.
result Trajectory prediction outperforms end-to-end control methods in autonomous racing simulations.
We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the training set. Our algorithm combines reinforcement learning and end-to-end imita…
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces. This provides one way of leveraging and combining the advantages of model-free and model-based approaches. Specifically, we differentiate through MPC by usin…
Convolutional neural networks are commonly used to control the steering angle for autonomous cars. Most of the time, multiple long range cameras are used to generate lateral failure cases. In this paper we present a novel model to generate this data and label augmentation using only one short range fisheye camera. We p…
Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control…
End-to-end deep reinforcement learning has enabled agents to learn with little preprocessing by humans. However, it is still difficult to learn stably and efficiently because the learning method usually uses a nonlinear function approximation. Neural Episodic Control (NEC), which has been proposed in order to improve s…
Uncertainty Quantification with Statistical Guarantees in End-to-End Autonomous Driving Controlcs.LG
Deep neural network controllers for autonomous driving have recently benefited from significant performance improvements, and have begun deployment in the real world. Prior to their widespread adoption, safety guarantees are needed on the controller behaviour that properly take account of the uncertainty within the mod…
Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However, deep learning-based perception has been shown to be vulnerable to a host of subtle …
Deep learning has revolutionized the ability to learn "end-to-end" autonomous vehicle control directly from raw sensory data. While there have been recent extensions to handle forms of navigation instruction, these works are unable to capture the full distribution of possible actions that could be taken and to reason a…
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, …
New neural methods for stable control with provable guarantees.
problem Designing stable control policies for nonlinear systems.
method Neural network Lyapunov functions and a falsifier to guide learning.
result Provable stability of controlled nonlinear systems.
End-to-end autonomous driving models get better uncertainty estimates.
problem Uncertainty quantification for end-to-end autonomous driving models.
method Approximate inference for implicit copula neural linear model.
result Densities for steering angle are marginally calibrated.
Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANscs.LG
Even though end-to-end supervised learning has shown promising results for sensorimotor control of self-driving cars, its performance is greatly affected by the weather conditions under which it was trained, showing poor generalization to unseen conditions. In this paper, we show how knowledge can be transferred using …
NDPs embed dynamical systems into neural networks for efficient sensorimotor learning.
problem Training policies directly in raw action spaces limits scalability for continuous tasks.
method Embed dynamical systems into neural networks to learn robot behaviors via demonstrations.
result NDPs outperform prior methods in both imitation and reinforcement learning setups.
Machine reading using differentiable reasoning models has recently shown remarkable progress. In this context, End-to-End trainable Memory Networks, MemN2N, have demonstrated promising performance on simple natural language based reasoning tasks such as factual reasoning and basic deduction. However, other tasks, namel…
Existing model-based reinforcement learning methods often study perception modeling and decision making separately. We introduce joint Perception and Control as Inference (PCI), a general framework to combine perception and control for partially observable environments through Bayesian inference. Based on the fact that…
Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception has been shown to be vulnerable to a host of subtle adversarial…
Algorithm reduces regret in partially observable systems by learning dynamics and using optimistic control.
problem Minimizing regret in partially observable linear quadratic control systems with unknown dynamics.
method ExpCommit algorithm that learns model parameters and uses optimism in uncertainty.
result End-to-end sublinear regret upper bound of for ExpCommit.
AugurOne trains single image generators without GANs using image warps.
problem Training end-to-end single image generators without GANs.
method Non-affine augmentations of single input images for training an upscaling neural network.
result End-to-end training yields state-of-the-art performance on conditional generation tasks.
We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's parameters. In the machine learning setting this brings CEM insi…
A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from significant performance improvements, with millions of miles having been driven wit…
In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed con…
Neural system optimizes glucose levels in diabetics.
problem Limited research on continuous glucose maintenance devices.
method Differential predictive control with neural policy and differentiable modeling.
result Improves glucose level optimization in real-time.
Framework for precise recall control in spatial conflation tasks.
problem Precise recall control in large-scale spatial conflation tasks to avoid downstream analytics failures and excessive manual review.
method End-to-end framework using equigrid bounding-box filter, CSR representation, neural ranker, and inverse-variance weighted ensemble of threshold estimators.
result Achieves exact recall with sub-percent variance over tens of millions of geometry pairs, runs on a single TPU v3 core.
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown. We propose a multi-stage procedure, called Coarse-ID control, that estimates a model from a few experimental trials, estimates the error in that model with respect to the truth, and then d…
Proposes neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics.
problem Understanding and modeling nonlinear dynamical systems.
method Trains neural networks to minimize forecast error based on spectral decomposition in the lifted space.
result Demonstrates effectiveness in eigenvalue estimation and forecast performance.
Disentangling Controllable Object through Video Prediction Improves Visual Reinforcement Learningcs.LG
A framework disentangles controllable objects from visual signals for improved RL.
problem Improving sample efficiency and game performance in vision-based RL.
method Action-conditioned video prediction to disentangle controllable objects.
result Improved sample efficiency and game performance in Atari games.
Myriad offers a testbed for integrating machine learning and trajectory optimization.
problem Real-world trajectory optimization challenges.
method JAX-based testbed with machine learning and trajectory optimization integration.
result End-to-end learning and planning with neural ODEs.
Novel method controls complex physical systems over long time frames.
problem Controlling complex nonlinear physical systems over long time frames.
method Hierarchical predictor-corrector scheme with separate planning and control networks.
result Successfully controls complex physical systems like incompressible Navier-Stokes equations.
End-to-end framework optimizes constrained trajectories using data-driven methods.
problem Optimizing trajectories under constraints with limited dynamics knowledge.
method Data-driven approach decomposes trajectories into function basis, uses maximum a posteriori for optimization, and incorporates linear constraints.
result Commanding results in aeronautics and sailing route optimization.
NeurT-FDR controls FDR by incorporating feature hierarchy.
problem Controlling FDR in complex, large-scale hypothesis testing problems.
method NeurT-FDR uses a neural network to parametrize test-level covariates and a regression framework to adjust feature hierarchy.
result NeurT-FDR makes substantially more discoveries than competitive baselines.
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a cont…
Neural networks struggle with TSP beyond small instances, requiring new approaches.
problem Neural networks struggle to generalize to larger instances of the TSP.
method Unified pipeline to identify inductive biases and promote generalization.
result Zero-shot generalization requires rethinking neural combinatorial optimization.
New controller reduces regret in non-stochastic control with adversarial perturbations.
problem Non-stochastic control with adversarial perturbations and partially observed states.
method Denoised observations and online gradient descent.
result Sublinear regret bounds, optimal for known and unknown systems.
Proposes a new reinforcement learning method to improve agent performance in control tasks.
problem Shortcomings of maximum likelihood estimation in model-based reinforcement learning.
method Directly optimizes expected returns using implicit differentiation of a Bellman optimality function.
result Empirical evidence shows improved performance in model misspecification regime.
NeurT-FDR controls FDR by incorporating auxiliary covariates in deep learning.
problem Controlling FDR in complex large-scale problems with indirect relations among covariates.
method NeurT-FDR uses a deep Black-Box framework that parametrizes test-level covariates as a neural network and adjusts auxiliary covariates through a regression framework.
result NeurT-FDR makes substantially more discoveries in real datasets compared to competitive baselines.
Unified approach to guided generation techniques.
problem Controlling the generative process of flow/diffusion models.
method Unified posterior and end-to-end guidance techniques.
result Unified posterior guidance as a greedy strategy of end-to-end guidance.
Improved robustness of 1D CNNs for heart arrhythmia classification.
problem Improving the robustness of 1D CNNs for classification tasks.
method Parameterization using Cayley transform and controllability Gramian for Lipschitz-bounded CNNs.
result Improved robustness of trained Lipschitz-bounded 1D CNNs for heart arrhythmia classification.
End-to-end learnable Gaussian mixture priors improve diffusion models' exploration and expressiveness.
problem Challenges in diffusion models when priors differ from target distributions.
method End-to-end learnable Gaussian mixture priors (GMPs) with iterative refinement.
result Significant performance improvements across various benchmark problems.
Paper introduces a method to infer causal direction from limited data.
problem Inference of causal direction from limited observational data.
method Meta learning combined with causal inference to create a generative model.
result The method accurately infers causal direction across various dataset sizes.
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the D2NN itself. By pruning unnecessary computation depending on input, D2NNs provide a…
Learning optimal feedback control laws capable of executing optimal trajectories is essential for many robotic applications. Such policies can be learned using reinforcement learning or planned using optimal control. While reinforcement learning is sample inefficient, optimal control only plans an optimal trajectory fr…
In this paper, we present a new open source toolkit for automatic speech recognition (ASR), named CAT (CRF-based ASR Toolkit). A key feature of CAT is discriminative training in the framework of conditional random field (CRF), particularly with connectionist temporal classification (CTC) inspired state topology. CAT co…
New method handles robust and adaptive control of linear systems with non-convex costs.
problem Robust and adaptive control of linear systems with unknown parameters.
method Combining non-asymptotic linear regression, interval prediction, and tree-based planning.
result First end-to-end suboptimality analysis for robust and adaptive MPC with non-convex costs.