ellariel/ln-one-shot-path-planning

Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network

Working paper

APA

Danila Valko and Daniel Kudenko (2023). Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network. In Proc. of the Adaptive and Learning Agents Workshop (ALA 2023) at AAMAS 2023, Cruz, Hayes, Wang, Yates (eds.), May 29-30, 2023, London, UK, https://alaworkshop2023.github.io/papers/ALA2023_paper_40.pdf`

BibTeX

@inproceedings{Valko2023,
author = {Danila Valko and Daniel Kudenko},
title = {Increasing Energy Efficiency of Bitcoin Infrastructure with Reinforcement Learning and One-shot Path Planning for the Lightning Network},
year = {2023},
publisher = {Cruz, Hayes, Wang, Yates (eds.)},
address = {London, UK},
url = {https://alaworkshop2023.github.io/papers/ALA2023_paper_40.pdf},
booktitle = {Proc. of the Adaptive and Learning Agents Workshop (ALA 2023) at AAMAS 2023, May 29-30},
location = {London, UK},
series = {ALA 2023}
}

Sources and References

• Native pathfinding algorithms are based on (Kumble & Roos, 2021); (Kumble, Epema & Roos, 2021); see also, GitHub.
• Carbon emissions were measured with CodeCarbon package.
• Experiments were run on a snapshot of the Lightning Network obtained from (Decker, 2020).
• The ForestFire sampling method was introduced in (Leskovec & Faloutsos, 2006); see also, GitHub.
• Note that one-shot path planning for 2D and 3D environments using fully convolutional neural network was introduced in (Kulvicius et al., 2020).