相关论文: Modified Double DQN: addressing stability

We analyze the DQN reinforcement learning algorithm as a stochastic approximation scheme using the o.d.e. (for 'ordinary differential equation') approach and point out certain theoretical issues. We then propose a modified scheme called…

This paper introduces a novel type of memetic algorithm based Topology and Weight Evolving Artificial Neural Network (TWEANN) system called DX Neural Network (DXNN). DXNN implements a number of interesting features, amongst which is: a…

We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in…

In this paper, a novel Deep Q-Network (DQN) based scheduling method to optimize delay time and fairness among entanglement requests in quantum repeater networks is proposed. The scheduling of requests determines which pairs of end nodes…

Std $Q$-target is a conservative, actor-critic, ensemble, $Q$-learning-based algorithm, which is based on a single key $Q$-formula: $Q$-networks standard deviation, which is an "uncertainty penalty", and, serves as a minimalistic solution…

Drones equipped with overhead manipulators offer unique capabilities for inspection, maintenance, and contact-based interaction. However, the motion of the drone and its manipulator is tightly linked, and even small attitude changes caused…

Non-stationary environments pose a fundamental challenge for deep reinforcement learning, as changes in dynamics or rewards invalidate learned value functions and cause catastrophic forgetting. We propose \emph{Gradient-Boosted Deep…

Mixed precision quantization has become an important technique for optimizing the execution of deep neural networks (DNNs). Certified robustness, which provides provable guarantees about a model's ability to withstand different adversarial…

Recently, there has been a wealth of effort devoted to the design of secure protocols for machine learning tasks. Much of this is aimed at enabling secure prediction from highly-accurate Deep Neural Networks (DNNs). However, as DNNs are…

Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count…

In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning…

Convolutional Neural Networks (CNNs) and their quantized counterparts are vulnerable to extraction attacks, posing a significant threat of IP theft. Yet, the robustness of quantized models against these attacks is little studied compared to…

Distributed computing is critically important for modern statistical analysis. Herein, we develop a distributed quasi-Newton (DQN) framework with excellent statistical, computation, and communication efficiency. In the DQN method, no…

Automated lane change is one of the most challenging task to be solved of highly automated vehicles due to its safety-critical, uncertain and multi-agent nature. This paper presents the novel deployment of the state of art Q learning…

To accelerate and compress deep neural networks (DNNs), many network quantization algorithms have been proposed. Although the quantization strategy of any algorithm from the state-of-the-arts may outperform others in some network…

Sample efficiency is a crucial problem in deep reinforcement learning. Recent algorithms, such as REDQ and DroQ, found a way to improve the sample efficiency by increasing the update-to-data (UTD) ratio to 20 gradient update steps on the…

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values…

This research project presents the implementation of a Deep Q-Learning Network (DQN) for a self-driving car on a 2-dimensional (2D) custom track, with the objective of enhancing the DQN network's performance. It encompasses the development…

Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static…

This work proposes a distributed algorithm for solving empirical risk minimization problems, called L-DQN, under the master/worker communication model. L-DQN is a distributed limited-memory quasi-Newton method that supports asynchronous…