Oracles & followers: Stackelberg equilibria in deep multi-agent reinforcement learning
Stackelberg equilibria arise naturally in a range of popular learning problems, such as in
security games or indirect mechanism design, and have received increasing attention in the …
security games or indirect mechanism design, and have received increasing attention in the …
Blockchain-empowered resource allocation in Multi-UAV-enabled 5G-RAN: a multi-agent deep reinforcement learning approach
In 5G and B5G networks, real-time and secure resource allocation with the common telecom
infrastructure is challenging. This problem may be more severe when mobile users are …
infrastructure is challenging. This problem may be more severe when mobile users are …
Coordinating followers to reach better equilibria: End-to-end gradient descent for stackelberg games
A growing body of work in game theory extends the traditional Stackelberg game to settings
with one leader and multiple followers who play a Nash equilibrium. Standard approaches …
with one leader and multiple followers who play a Nash equilibrium. Standard approaches …
Dynamic pricing optimization for commercial subcontracting power suppliers engaging demand response considering building virtual energy storage
H Huang, Y Ning, Y Jiang, Z Tang, Y Qian… - Frontiers in Energy …, 2024 - frontiersin.org
Commercial buildings have abundant flexible energy resources for demand response (DR).
The electricity price for tenants in the commercial building is generally issued by a …
The electricity price for tenants in the commercial building is generally issued by a …
Navigating in a space of game views
Game-theoretic modeling entails selecting the particular elements of a complex strategic
situation deemed most salient for strategic analysis. Recognizing that any game model is …
situation deemed most salient for strategic analysis. Recognizing that any game model is …
The Synergetic Effect in the Management of Active System with Distributed Control
The synergetic reasonability of joining the efforts of the centers of competence in the
management of certain object participating in the game has been proved based on a theory …
management of certain object participating in the game has been proved based on a theory …
ReLExS: Reinforcement Learning Explanations for Stackelberg No-Regret Learners
X Huang, J Li, J **e - arxiv preprint arxiv:2408.14086, 2024 - arxiv.org
With the constraint of a no regret follower, will the players in a two-player Stackelberg game
still reach Stackelberg equilibrium? We first show when the follower strategy is either reward …
still reach Stackelberg equilibrium? We first show when the follower strategy is either reward …
Integrating Machine Learning and Optimization with Applications in Public Health and Sustainability
K Wang - 2023 - search.proquest.com
The field of artificial intelligence (AI) has garnered increasing attention in the realms of
public health and conservation due to its potential to characterize complex dynamics and …
public health and conservation due to its potential to characterize complex dynamics and …
[BUCH][B] Learning and Decision-Making in Competitive and Uncertain Systems
T Fiez - 2021 - search.proquest.com
As a result of the demonstrated potential for impact in traditional use cases, progressively
more is being asked of machine learning methods. This evolution has lead to a renewed …
more is being asked of machine learning methods. This evolution has lead to a renewed …
Incentives for individual compliance with pandemic response measures
The common methods to fight against COVID-19 are quasi-standard measures which
include wearing masks, social distancing and vaccination. However, combining these …
include wearing masks, social distancing and vaccination. However, combining these …