English
Related papers

Related papers: Target Networks and Over-parameterization Stabiliz…

200 papers

Bootstrapping is behind much of the successes of deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to…

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

Machine Learning · Computer Science 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

The deadly triad refers to the instability of a reinforcement learning algorithm when it employs off-policy learning, function approximation, and bootstrapping simultaneously. In this paper, we investigate the target network as a tool for…

Machine Learning · Computer Science 2023-10-02 Shangtong Zhang , Hengshuai Yao , Shimon Whiteson

Recent results in supervised learning suggest that while overparameterized models have the capacity to overfit, they in fact generalize quite well. We ask whether the same phenomenon occurs for offline contextual bandits. Our results are…

Machine Learning · Computer Science 2021-06-17 David Brandfonbrener , William F. Whitney , Rajesh Ranganath , Joan Bruna

We propose and analyze an alternate approach to off-policy multi-step temporal difference learning, in which off-policy returns are corrected with the current Q-function in terms of rewards, rather than with the target policy in terms of…

Artificial Intelligence · Computer Science 2016-08-12 Anna Harutyunyan , Marc G. Bellemare , Tom Stepleton , Remi Munos

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

Integral to recent successes in deep reinforcement learning has been a class of temporal difference methods that use infrequently updated target values for policy evaluation in a Markov Decision Process. Yet a complete theoretical…

Machine Learning · Computer Science 2023-08-15 Mattie Fellows , Matthew J. A. Smith , Shimon Whiteson

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

$Q$-learning with function approximation is one of the most empirically successful while theoretically mysterious reinforcement learning (RL) algorithms, and was identified in Sutton (1999) as one of the most important theoretical open…

Machine Learning · Computer Science 2022-05-04 Zaiwei Chen , John Paul Clarke , Siva Theja Maguluri

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

We identify an implicit under-parameterization phenomenon in value-based deep RL methods that use bootstrapping: when value functions, approximated using deep neural networks, are trained with gradient descent using iterated regression onto…

Machine Learning · Computer Science 2021-10-26 Aviral Kumar , Rishabh Agarwal , Dibya Ghosh , Sergey Levine

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these techniques in general yield…

Machine Learning · Computer Science 2020-07-28 Ilya Kostrikov , Ofir Nachum

Training a classifier under non-convex constraints has gotten increasing attention in the machine learning community thanks to its wide range of applications such as algorithmic fairness and class-imbalanced classification. However, several…

Machine Learning · Statistics 2022-10-31 You-Lin Chen , Zhaoran Wang , Mladen Kolar

We develop a neural-network framework for multi-period risk--reward stochastic control problems with constrained two-step feedback policies that may be discontinuous in the state. We allow a broad class of objectives built on a…

Computational Finance · Quantitative Finance 2026-03-09 Chang Chen , Duy-Minh Dang

Multi-objective Markov decision processes are a special kind of multi-objective optimization problem that involves sequential decision making while satisfying the Markov property of stochastic processes. Multi-objective reinforcement…

Machine Learning · Computer Science 2023-08-22 Sherif Abdelfattah , Kathryn Kasmarik , Jiankun Hu

Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and…

Machine Learning · Computer Science 2019-11-26 Aviral Kumar , Justin Fu , George Tucker , Sergey Levine

Model predictive control can optimally deal with nonlinear systems under consideration of constraints. The control performance depends on the model accuracy and the prediction horizon. Recent advances propose to use reinforcement learning…

Machine Learning · Computer Science 2024-11-01 Dean Brandner , Sergio Lucia

This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…

Machine Learning · Computer Science 2018-11-08 Sina Ghiassian , Andrew Patterson , Martha White , Richard S. Sutton , Adam White

Overparameterization, the condition where models have more parameters than necessary to fit their training loss, is a crucial factor for the success of deep learning. However, the characteristics of the features learned by overparameterized…

Machine Learning · Computer Science 2024-07-02 Ahmet Cagri Duzgun , Samy Jelassi , Yuanzhi Li
‹ Prev 1 2 3 10 Next ›