Soft Actor-Critic Deep Reinforcement Learning Based Interference Resource Allocation

Rao, Ning; Xu, Hua; Song, Balin; Shi, Yunhao

doi:10.1145/3467707.3467766

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the subsequent evolution of the SAC algorithm, the loss function 𝐿(𝛼) of the entropy regularization term 𝛼 was added to achieve the function of automatically updating the entropy regularization term 𝛼 (Rao et al 2021) [37], as shown in (12).…”

Section: Selection Of Policy Iteration Methods In Cql Algorithmmentioning

confidence: 99%

Automatic Tracking Control Strategy of Autonomous Trains Considering Speed Restrictions: Using the Improved Offline Deep Reinforcement Learning Method

Liu,

Feng,

Xiao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Previous research on automatic control of high-speed trains in speed limit sections is insufficient. This article proposes a new offline reinforcement learning strategy for automatic tracking of autonomous trains. Firstly, the operating speed and deceleration starting point were determined for different speed limit scenarios. Then, a tracking controller based on the improved offline conservative Q-learning (CQL) algorithm was designed to avoid frequent interaction between the train and the environment. Selected an appropriate policy to implement the CQL algorithm. The data samples were reclassified to increase sample concentration. The value and strategy network structure was redesigned. The state space and action space of tracking trains were limited, and the dimension of state space was increased. A multi-objective reward function was designed to distinguish the tracking process of trains in different sections. The simulation results show that the proposed high-speed railway tracking interval automatic control algorithm is superior to traditional online reinforcement learning methods in terms of safety, comfort, and convergence efficiency.

show abstract

Section: Selection Of Policy Iteration Methods In Cql Algorithmmentioning

confidence: 99%