Comparison of Reinforcement Learning Based Control Algorithms for One Autonomous Driving Problem

Kabanov, Stepan; Mitiai, German; Wu, Haitao; Petrosian, Ovanes

doi:10.1007/978-3-031-16224-4_24

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tuning of the hyperparameters of DDPG is tricky and obtaining a stable training result may be difficult [36]. Compared to the methods above, PPO addresses these concerns by being easily tuned and easy to implement, showing a very fast convergence rate [37]. PPO [38] utilizes an actor-critic framework and features a parameterized actor that can enforce a trust region using clipped objectives.…”

Section: A Decision-making Methodsmentioning

confidence: 99%

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

et al. 2022

View full text Add to dashboard Cite

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy. However, precise detection remains a considerable challenge due to subtle variabilities across subjects, channels and time points. Thus, capturing fine-grained, discriminative features of EEG patterns, which is associated with high-frequency textural information, is yet to be resolved. In this work, we propose Scattering Transformer (ScatterFormer), an invariant scattering transform-based hierarchical Transformer that specifically pays attention to subtle features. In particular, the disentangled frequency-aware attention (FAA) enables the Transformer to capture clinically informative high-frequency components, offering a novel clinical explainability based on visual encoding of multichannel EEG signals. Evaluations on two distinct tasks of epileptiform detection demonstrate the effectiveness our method. Our proposed model achieves median AUCROC and accuracy of 98.14%, 96.39% in patients with Rolandic epilepsy. On a neonatal seizure detection benchmark, it outperforms the state-of-the-art by 9% in terms of average AUCROC.

show abstract

Section: A Decision-making Methodsmentioning

confidence: 99%

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

et al. 2022

View full text Add to dashboard Cite

show abstract

Multi-agent Reinforcement Learning-based Adaptive Heterogeneous DAG Scheduling

Zhadan,

Allahverdyan,

Kondratov

et al. 2023

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

Static scheduling of computational workflow represented by a directed acyclic graph (DAG) is an important problem in many areas of computer science. The main idea and novelty of the proposed algorithm is an adaptive heuristic or graph metric which uses a different heuristic rule at each scheduling step depending on local workflow. It is also important to note that multi-agent reinforcement learning is used to determine scheduling policy based on adaptive metrics. In order to prove the efficiency of the approach a comparison with the state-of-the-art DAG scheduling algorithms is provided: DONF, CPOP, HCPT, HPS and PETS. Based on the simulation results the proposed algorithm shows the improvement of up to 30% on specific graph topologies, and average performance gain of 5.32% compared to the best scheduling algorithm DONF(suitable for large-scale scheduling) on large number of random DAGs. Another important result is that using the proposed algorithm it was possible to cover 30.01% of the proximity interval from the best scheduling algorithm to the global optimal solution. This indicates that the idea of an adaptive metric for DAG scheduling is important and requires further research and development.

show abstract

Comparison of Reinforcement Learning Based Control Algorithms for One Autonomous Driving Problem

Cited by 2 publications

References 26 publications

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

The Shanghai alliance of multilingual researchers: Fudan University, Tongji University, Shanghai University of Finance and Economics, and Shanghai International Studies University, China

Multi-agent Reinforcement Learning-based Adaptive Heterogeneous DAG Scheduling

Contact Info

Product

Resources

About