SACNN: Self Attention-Based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports
Abstract
In this paper, we investigate the issue of error accumulation in critic networks updated via pessimistic temporal difference objectives. We show that the critic approximation error can be approximated via a recursive fixed-point model similar to that of the Bellman value. We use such recursive definition to retrieve the conditions under which the pessimistic critic is unbiased. Building on these insights, we propose Validation Pessimism Learning (VPL) algorithm. VPL uses a small validation buffer to adjust the levels of pessimism throughout the agent training, with the pessimism set such that the approximation error of the critic targets is minimized. We investigate the proposed approach on a variety of locomotion and manipulation tasks and report improvements in sample efficiency and performance.
Cite
Text
Rahman et al. "SACNN: Self Attention-Based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/665Markdown
[Rahman et al. "SACNN: Self Attention-Based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/rahman2024ijcai-sacnn/) doi:10.24963/ijcai.2024/665BibTeX
@inproceedings{rahman2024ijcai-sacnn,
title = {{SACNN: Self Attention-Based Convolutional Neural Network for Fraudulent Behaviour Detection in Sports}},
author = {Rahman, Maxx Richard and Khaliq, Lotfy H. Abdel and Piper, Thomas and Geyer, Hans and Equey, Tristan and Baume, Norbert and Aikin, Reid and Maass, Wolfgang},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {6017-6025},
doi = {10.24963/ijcai.2024/665},
url = {https://mlanthology.org/ijcai/2024/rahman2024ijcai-sacnn/}
}