An essential prerequisite for proactive and anticipatory real-time regulation of railroad traffic is the accurate forecast of train delays, or deviations from the schedule. To manage the viability of timetable realiza...
详细信息
Ideological and political education is a crucial part of the education system for university students in China. However, traditional teaching methods face challenges such as weak classroom interaction and insufficient...
详细信息
Most reinforcement learningalgorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction w...
详细信息
ISBN:
(纸本)1577358872
Most reinforcement learningalgorithms seek a single optimal strategy that solves a given task. However, it can often be valuable to learn a diverse set of solutions, for instance, to make an agent's interaction with users more engaging, or improve the robustness of a policy to an unexpected perturbance. We propose Diversity-Guided Policy optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task. Unlike prior work, it achieves this with a shared policy network trained over a single run. Specifically, we design an intrinsic reward based on an information-theoretic diversity objective. Our final objective alternately constraints on the diversity of the strategies and on the extrinsic reward. We solve the constrained optimization problem by casting it as a probabilistic inference task and use policy iteration to maximize the derived lower bound. Experimental results show that our method efficiently discovers diverse strategies in a wide variety of reinforcement learning tasks. Compared to baseline methods, DGPO achieves comparable rewards, while discovering more diverse strategies, and often with better sample efficiency.
Parkinson's disease (PD) is a neuro-degenerative disease caused due to breakdown of brain cells in the central-part of the nervous system. As symptoms of PD appear only after 60% or more of these cells are destroy...
详细信息
the rapid growth of embedded systems has led to the integration of artificial intelligence capabilities at the edge of computer devices. the Beagle-Bone AI and AI64 platform is a potent development board intended to m...
详细信息
Voltage control in low-observable distribution networks faces significant uncertainty challenges. In this paper, an uncertainty-aware voltage control method based on the fusion of Bayesian deep learning and probabilis...
详细信息
Intrusion detection is crucial for securing IoT networks amid the rapid proliferation of devices, posing significant security challenges. this study offers a unique intrusion detection model for IoT deep learning meth...
详细信息
the Internet of things (IoT) enabled Wireless Sensor Network (WSN) has been rapidly growing in popularity due to its ability to quickly connect various sensor nodes and provide a network of connected devices. Intellig...
详细信息
Withthe rapid expansion of 5G networks, the number of base stations and their energy consumption have significantly increased, making energy efficiency a critical challenge. To address this issue, this paper proposes...
详细信息
the rapid development and increasing popularity of wearable technologies have drawn substantial attention from firms seeking to expand into new markets and innovate in the healthcare industry. As electronic devices em...
详细信息
暂无评论