English
Related papers

Related papers: Natural Gradient Deep Q-learning

200 papers

Quantum machine learning has the potential for a transformative impact across industry sectors and in particular in finance. In our work we look at the problem of hedging where deep reinforcement learning offers a powerful framework for…

To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greedification operators to iteratively improve it. The reliance…

This paper provides a theoretical understanding of Deep Q-Network (DQN) with the $\varepsilon$-greedy exploration in deep reinforcement learning. Despite the tremendous empirical achievement of the DQN, its theoretical characterization…

Machine Learning · Computer Science 2023-10-26 Shuai Zhang , Hongkang Li , Meng Wang , Miao Liu , Pin-Yu Chen , Songtao Lu , Sijia Liu , Keerthiram Murugesan , Subhajit Chaudhury

We study reinforcement learning (RL) in high dimensional episodic Markov decision processes (MDP). We consider value-based RL when the optimal Q-value is a linear function of d-dimensional state-action feature representation. For instance,…

Artificial Intelligence · Computer Science 2019-09-10 Kamyar Azizzadenesheli , Animashree Anandkumar

In this paper, we propose a novel deep Q-network (DQN)-based edge selection algorithm designed specifically for real-time surveillance in unmanned aerial vehicle (UAV) networks. The proposed algorithm is designed under the consideration of…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-09-22 Soohyun Park , Jeman Park , David Mohaisen , Joongheon Kim

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions…

Artificial Intelligence · Computer Science 2025-09-10 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

In human decision-making tasks, individuals learn through trials and prediction errors. When individuals learn the task, some are more influenced by good outcomes, while others weigh bad outcomes more heavily. Such confirmation bias can…

Machine Learning · Computer Science 2024-08-09 Jiacheng Shen , Lihan Feng

In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions.…

Artificial Intelligence · Computer Science 2024-06-24 Carlos Núñez-Molina , Juan Fernández-Olivares , Raúl Pérez

We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad…

This work presents a new algorithm for training recurrent neural networks (although ideas are applicable to feedforward networks as well). The algorithm is derived from a theory in nonconvex optimization related to the diffusion equation.…

Machine Learning · Computer Science 2016-02-08 Hossein Mobahi

The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, target networks notoriously require additional memory and delay…

Machine Learning · Computer Science 2026-03-02 Théo Vincent , Yogesh Tripathi , Tim Faust , Abdullah Akgül , Yaniv Oren , Melih Kandemir , Jan Peters , Carlo D'Eramo

Quantum machine learning holds the promise of harnessing quantum advantage to achieve speedup beyond classical algorithms. Concurrently, research indicates that dissipation can serve as an effective resource in quantum computation. In this…

Quantum Physics · Physics 2024-08-29 He Wang , Jin Wang

We propose a new technique that boosts the convergence of training generative adversarial networks. Generally, the rate of training deep models reduces severely after multiple iterations. A key reason for this phenomenon is that a deep…

Machine Learning · Statistics 2018-06-15 Atsushi Nitanda , Taiji Suzuki

Gradient descent methods have long been the de facto standard for training deep neural networks. Millions of training samples are fed into models with billions of parameters, which are slowly updated over hundreds of epochs. Recently, it's…

Machine Learning · Computer Science 2023-02-14 Tim Whitaker

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research…

Software Engineering · Computer Science 2021-12-07 Basel Magableh

This paper explores the problem of simultaneously learning a value function and policy in deep actor-critic reinforcement learning models. We find that the common practice of learning these functions jointly is sub-optimal, due to an…

Machine Learning · Computer Science 2022-11-15 Matthew Aitchison , Penny Sweetser

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

In many real-world multi-robot tasks, high-quality solutions often require a team of robots to perform asynchronous actions under decentralized control. Decentralized multi-agent reinforcement learning methods have difficulty learning…

Robotics · Computer Science 2020-03-05 Yuchen Xiao , Joshua Hoffman , Tian Xia , Christopher Amato

This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the…

Machine Learning · Computer Science 2018-11-21 Felix Leibfried , Peter Vrancx

We study the action generalization ability of deep Q-learning in discrete action spaces. Generalization is crucial for efficient reinforcement learning (RL) because it allows agents to use knowledge learned from past experiences on new…

Artificial Intelligence · Computer Science 2022-05-12 Zhiyuan Zhou , Cameron Allen , Kavosh Asadi , George Konidaris