English
Related papers

Related papers: Non-Uniform Noise-to-Signal Ratio in the REINFORCE…

200 papers

Despite the empirical success of meta reinforcement learning (meta-RL), there are still a number poorly-understood discrepancies between theory and practice. Critically, biased gradient estimates are almost always implemented in practice,…

Machine Learning · Computer Science 2021-12-15 Yunhao Tang

Second-order information -- such as curvature or data covariance -- is critical for optimisation, diagnostics, and robustness. However, in many modern settings, only the gradients are observable. We show that the gradients alone can reveal…

Machine Learning · Computer Science 2026-04-08 Arash Jamshidi , Katsiaryna Haitsiukevich , Kai Puolamäki

Reliable state estimation is essential for autonomous systems operating in complex, noisy environments. Classical filtering approaches, such as the Kalman filter, can struggle when facing nonlinear dynamics or non-Gaussian noise, and even…

Machine Learning · Computer Science 2025-04-11 Wonjin Song , Feng Bao

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…

Machine Learning · Computer Science 2025-06-11 Haozhe Ma , Guoji Fu , Zhengding Luo , Jiele Wu , Tze-Yun Leong

Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…

Computation and Language · Computer Science 2015-07-16 D. S. Pavan Kumar

Risk-averse reinforcement learning (RARL) is critical for decision-making under uncertainty, which is especially valuable in high-stake applications. However, most existing works focus on risk measures, e.g., conditional value-at-risk…

Machine Learning · Computer Science 2025-04-16 Yudong Luo , Yangchen Pan , Jiaqi Tan , Pascal Poupart

Deep neural networks (DNNs) have achieved remarkable success across diverse domains, but their performance can be severely degraded by noisy or corrupted training data. Conventional noise mitigation methods often rely on explicit…

Machine Learning · Computer Science 2025-06-16 Deliang Jin , Gang Chen , Shuo Feng , Yufeng Ling , Haoran Zhu

We present a class of systems for which the signal-to-noise ratio always increases when increasing the noise and diverges at infinite noise level. This new phenomenon is a direct consequence of the existence of a scaling law for the…

Condensed Matter · Physics 2016-08-15 J. M. G. Vilar , J. M. Rubí

In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a policy that optimizes a linear function of its state-action…

Machine Learning · Computer Science 2023-08-30 Navdeep Kumar , Kaixin Wang , Kfir Levy , Shie Mannor

Networks are widely used in many fields for their powerful ability to provide vivid representations of relationships between variables. However, many of them may be corrupted by experimental noise or inappropriate network inference methods…

Molecular Networks · Quantitative Biology 2021-09-21 Jiating Yu , Jiacheng Leng , Ling-Yun Wu

Recurrent spiking neural networks (RSNNs) are a promising substrate for energy-efficient control policies, but training them for high-dimensional, long-horizon reinforcement learning remains challenging. Population-based, gradient-free…

Machine Learning · Computer Science 2026-01-30 Jinhao Li , Yuhao Sun , Zhiyuan Ma , Hao He , Xinche Zhang , Xing Chen , Jin Li , Sen Song

Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy…

Machine Learning · Computer Science 2021-10-12 Osbert Bastani

We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of…

Systems and Control · Computer Science 2018-10-30 Ming Jin , Javad Lavaei

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…

Machine Learning · Computer Science 2023-11-02 Udaya Ghai , Arushi Gupta , Wenhan Xia , Karan Singh , Elad Hazan

Deep neural networks achieve high prediction accuracy when the train and test distributions coincide. In practice though, various types of corruptions occur which deviate from this setup and cause severe performance degradations. Few…

Machine Learning · Computer Science 2023-05-30 Theodoros Tsiligkaridis , Athanasios Tsiligkaridis

Reinforcement learning in non-stationary environments is challenging due to abrupt and unpredictable changes in dynamics, often causing traditional algorithms to fail to converge. However, in many real-world cases, non-stationarity has some…

Machine Learning · Computer Science 2025-03-25 Mohsen Amiri , Sindri Magnússon

Searching for gravitational-wave signals is a challenging and computationally intensive endeavor undertaken by multiple independent analysis pipelines. While detection depends only on observed noisy data, it is sometimes inconsistently…

General Relativity and Quantum Cosmology · Physics 2024-03-15 Matthew Mould , Christopher J. Moore , Davide Gerosa

Randomly perturbing networks during the training process is a commonly used approach to improving generalization performance. In this paper, we present a theoretical study of one particular way of random perturbation, which corresponds to…

Machine Learning · Computer Science 2021-02-16 Oussama Dhifallah , Yue M. Lu

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

Robotics · Computer Science 2024-12-02 Severin Bochem , Eduardo Gonzalez-Sanchez , Yves Bicker , Gabriele Fadini
‹ Prev 1 4 5 6 7 8 10 Next ›