English
Related papers

Related papers: Scaling Effects and Uncertainty Quantification in …

200 papers

Existing work on risk-sensitive reinforcement learning - both for symmetric and downside risk measures - has typically used direct Monte-Carlo estimation of policy gradients. While this approach yields unbiased gradient estimates, it also…

Machine Learning · Computer Science 2020-07-09 Thomas Spooner , Rahul Savani

This paper studies the networked multi-agent reinforcement learning (NMARL) problem, where the objective of agents is to collaboratively maximize the discounted average cumulative rewards. Different from the existing methods that suffer…

Multiagent Systems · Computer Science 2025-06-02 Pengcheng Dai , Yuanqiu Mo , Wenwu Yu , Wei Ren

It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exponentially large in the number of agents. In this paper, we…

Optimization and Control · Mathematics 2020-06-12 Guannan Qu , Yiheng Lin , Adam Wierman , Na Li

In this paper, we address the problem of estimating scale factors between images. We formulate the scale estimation problem as a prediction of a probability distribution over scale factors. We design a new architecture, ScaleNet, that…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Axel Barroso-Laguna , Yurun Tian , Krystian Mikolajczyk

In this article, we study approximation properties of the variation spaces corresponding to shallow neural networks with a variety of activation functions. We introduce two main tools for estimating the metric entropy, approximation rates,…

Machine Learning · Statistics 2024-02-26 Jonathan W. Siegel , Jinchao Xu

Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly…

Machine Learning · Computer Science 2018-10-25 Esther Derman , Daniel J. Mankowitz , Timothy A. Mann , Shie Mannor

In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state. Asymmetric actor-critic methods exploit such…

Machine Learning · Computer Science 2022-08-08 Andrea Baisero , Christopher Amato

Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when…

Machine Learning · Computer Science 2021-05-19 Yue Wu , Shuangfei Zhai , Nitish Srivastava , Joshua Susskind , Jian Zhang , Ruslan Salakhutdinov , Hanlin Goh

Decentralized Actor-Critic (AC) algorithms have been widely utilized for multi-agent reinforcement learning (MARL) and have achieved remarkable success. Apart from its empirical success, the theoretical convergence property of decentralized…

Machine Learning · Computer Science 2023-01-31 Qijun Luo , Xiao Li

In this research, some of the issues that arise from the scalarization of the multi-objective optimization problem in the Advantage Actor Critic (A2C) reinforcement learning algorithm are investigated. The paper shows how a naive…

Machine Learning · Computer Science 2021-10-04 Federico A. Galatolo , Mario G. C. A. Cimino , Gigliola Vaglini

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan

Models are often given in terms of differential equations to represent physical systems. In the presence of uncertainty, accurate prediction of the behavior of these systems using the models requires understanding the effect of uncertainty…

Computational Physics · Physics 2020-08-12 Subhayan De

Scientists have been interested in estimating causal peer effects to understand how people's behaviors are affected by their network peers. However, it is well known that identification and estimation of causal peer effects are challenging…

Methodology · Statistics 2021-09-07 Naoki Egami , Eric J. Tchetgen Tchetgen

We present a training framework for neural abstractive summarization based on actor-critic approaches from reinforcement learning. In the traditional neural network based methods, the objective is only to maximize the likelihood of the…

Computation and Language · Computer Science 2018-08-16 Piji Li , Lidong Bing , Wai Lam

This work addresses the problem of ensuring trustworthy computation in a linear consensus network. A solution to this problem is relevant for several tasks in multi-agent systems including motion coordination, clock synchronization, and…

Optimization and Control · Mathematics 2011-04-19 Fabio Pasqualetti , Antonio Bicchi , Francesco Bullo

We revisit the standard formulation of tabular actor-critic algorithm as a two time-scale stochastic approximation with value function computed on a faster time-scale and policy computed on a slower time-scale. This emulates policy…

Machine Learning · Computer Science 2024-06-21 Shalabh Bhatnagar , Vivek S. Borkar , Soumyajit Guin

Predictive coding (PC) is a biologically plausible alternative to standard backpropagation (BP) that minimises an energy function with respect to network activities before updating weights. Recent work has improved the training stability of…

Machine Learning · Computer Science 2026-05-25 Francesco Innocenti , El Mehdi Achour , Rafal Bogacz

This paper proposes an improved training algorithm for binary neural networks in which both weights and activations are binary numbers. A key but fairly overlooked feature of the current state-of-the-art method of XNOR-Net is the use of…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Adrian Bulat , Georgios Tzimiropoulos

Off-policy Actor-Critic algorithms have demonstrated phenomenal experimental performance but still require better explanations. To this end, we show its policy evaluation error on the distribution of transitions decomposes into: a Bellman…

Machine Learning · Computer Science 2021-10-07 Ting-Han Fan , Peter J. Ramadge

Reusing previously trained models is critical in deep reinforcement learning to speed up training of new agents. However, it is unclear how to acquire new skills when objectives and constraints are in conflict with previously learned…

Machine Learning · Computer Science 2022-02-09 Jaime S. Ide , Daria Mićović , Michael J. Guarino , Kevin Alcedo , David Rosenbluth , Adrian P. Pope
‹ Prev 1 3 4 5 6 7 10 Next ›