Q-learning ≈ Q-learning
View article
Deep Reinforcement Learning with Double Q-Learning Open
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can genera…
View article
Q-Learning Algorithms: A Comprehensive Classification and Applications Open
Q-learning is arguably one of the most applied representative reinforcement learning approaches and one of the off-policy strategies. Since the emergence of Q-learning, many studies have described its uses in reinforcement learning and art…
View article
Conservative Q-Learning for Offline Reinforcement Learning Open
Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, sta…
View article
Multi-Agent Reinforcement Learning-Based Resource Allocation for UAV Networks Open
Unmanned aerial vehicles (UAVs) are capable of serving as aerial base stations (BSs) for providing both cost-effective and on-demand wireless communications. This article investigates dynamic resource allocation of multiple UAVs enabled co…
View article
Spectrum Sharing in Vehicular Networks Based on Multi-Agent Reinforcement Learning Open
This paper investigates the spectrum sharing problem in vehicular networks based on multi-agent reinforcement learning, where multiple vehicle-to-vehicle (V2V) links reuse the frequency spectrum preoccupied by vehicle-to-infrastructure (V2…
View article
Distributional Reinforcement Learning With Quantile Regression Open
In reinforcement learning (RL), an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in t…
View article
A Multi-Agent Reinforcement Learning-Based Data-Driven Method for Home Energy Management Open
This paper proposes a novel framework for home energy management (HEM) based on reinforcement learning in achieving efficient home-based demand response (DR). The concerned hour-ahead energy consumption scheduling problem is duly formulate…
View article
Continuous Deep Q-Learning with Model-based Acceleration Open
Model-free reinforcement learning has been successfully applied to a range of challenging problems, and has recently been extended to handle large neural network policies and value functions. However, the sample complexity of model-free al…
View article
Multi-Objective Workflow Scheduling With Deep-Q-Network-Based Multi-Agent Reinforcement Learning Open
Cloud Computing provides an effective platform for executing large-scale and complex workflow applications with a pay-as-you-go model. Nevertheless, various challenges, especially its optimal scheduling for multiple conflicting objectives,…
View article
Energy Management Strategy for a Hybrid Electric Vehicle Based on Deep Reinforcement Learning Open
An energy management strategy (EMS) is important for hybrid electric vehicles (HEVs) since it plays a decisive role on the performance of the vehicle. However, the variation of future driving conditions deeply influences the effectiveness …
View article
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction Open
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 actor…
View article
DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks Open
This paper proposes DeepRMSA, a deep reinforcement learning framework for routing, modulation and spectrum assignment (RMSA) in elastic optical networks (EONs). DeepRMSA learns the correct online RMSA policies by parameterizing the policie…
View article
Collision Avoidance in Pedestrian-Rich Environments With Deep Reinforcement Learning Open
Collision avoidance algorithms are essential for safe and efficient robot\noperation among pedestrians. This work proposes using deep reinforcement (RL)\nlearning as a framework to model the complex interactions and cooperation with\nnearb…
View article
High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning Open
Machine learning techniques have been shown to outperform many rule-based systems for the decision-making of autonomous vehicles. However, applying machine learning is challenging due to the possibility of executing unsafe actions and slow…
View article
Multi-Robot Path Planning Method Using Reinforcement Learning Open
This paper proposes a noble multi-robot path planning algorithm using Deep q learning combined with CNN (Convolution Neural Network) algorithm. In conventional path planning algorithms, robots need to search a comparatively wide area for n…
View article
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction Open
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 actor…
View article
Hyperparameter Optimization for Tracking with Continuous Deep Q-Learning Open
Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process. Selecting appropriate hyperparameters is critical for the accuracy of tracking algorithms, yet it is difficult to determine …
View article
Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning Open
Quantum machine learning (QML) has been identified as one of the key fields that could reap advantages from near-term quantum devices, next to optimization and quantum chemistry. Research in this area has focused primarily on variational q…
View article
Reinforcement Learning with Parameterized Actions Open
We introduce a model-free algorithm for learning in Markov decision processes with parameterized actions—discrete actions with continuous parameters. At each step the agent must select both which action to use and which parameters to use w…
View article
Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space Open
Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid actio…
View article
Distributional Reinforcement Learning with Quantile Regression Open
In reinforcement learning an agent interacts with the environment by taking actions and observing the next state and reward. When sampled probabilistically, these state transitions, rewards, and actions can all induce randomness in the obs…
View article
Cooperative Deep Q-Learning With Q-Value Transfer for Multi-Intersection Signal Control Open
The problem of adaptive traffic signal control in the multi-intersection system has attracted the attention of researchers. Among the existing methods, reinforcement learning has shown to be effective. However, the complex intersection fea…
View article
Dynamic Offloading for Multiuser Muti-CAP MEC Networks: A Deep Reinforcement Learning Approach Open
In this paper, we study a multiuser mobile edge computing (MEC) network, where tasks from users can be partially offloaded to multiple computational access points (CAPs). We consider practical cases where task characteristics and computati…
View article
Off-Policy Interleaved $Q$ -Learning: Optimal Control for Affine Nonlinear Discrete-Time Systems Open
In this paper, a novel off-policy interleaved Q-learning algorithm is presented for solving optimal control problem of affine nonlinear discrete-time (DT) systems, using only the measured data along the system trajectories. Affine nonlinea…
View article
Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels Open
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach…
View article
Relations between Model Predictive Control and Reinforcement Learning Open
In this paper relations between model predictive control and reinforcement learning are studied for discrete-time linear time-invariant systems with state and input constraints and a quadratic value function. The principles of model predic…
View article
A Theoretical Analysis of Deep Q-Learning Open
Despite the great empirical success of deep reinforcement learning, its theoretical foundation is less well understood. In this work, we make the first attempt to theoretically understand the deep Q-network (DQN) algorithm (Mnih et al., 20…
View article
Offline Reinforcement Learning with Implicit Q-Learning Open
Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as t…
View article
Path Planning via an Improved DQN-Based Learning Policy Open
The path planning technology is an important part of navigation, which is the core of robotics research. Reinforcement learning is a fashionable algorithm that learns from experience by mimicking the process of human learning skills. When …
View article
Comparative Analysis of Energy Management Strategies for HEV: Dynamic Programming and Reinforcement Learning Open
Energy management strategy is an important factor in determining the fuel economy of hybrid electric vehicles; thus, much research on how to distribute the required power to engines and motors of hybrid vehicles is required. Recently, vari…