Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
We study a bilevel economic system, which we refer to as a Markov exchange economy (MEE), from the point of view of multi-agent reinforcement learning ...
We study a bilevel economic system, which we refer to as a Markov exchange economy (MEE), from the point of view of multi-agent reinforce-.
The goal of each agent is to myopically maximize its own utility at each step, which leads to a Competitive. Equilibrium (CE) as the agents' subproblem. The ...
An al- algorithm is proposed, dubbed as MOLM, which combines the optimism principle for exploration with subgame CE seeking and can readily incorporate ...
People also ask
Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy ... Markov Exchange Economy (MEE) and provide two prov- ably ...
Jun 7, 2023 · The target of EE is to achieve Competitive Equilibrium (CE), where all agents maximize their own utilities under their budget constraint.
Jul 19, 2022 · Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy. Jul 19, 2022. Speakers. ZL · Zhihan Liu.
Codes for the ICML 2022 accepted paper: Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy. About.
Jan 1, 2022 · Welfare Maximization in Competitive Equilibrium: Reinforcement Learning for Markov Exchange Economy. Citation Details. Title: Welfare ...
Welfare maximization in competitive equilibrium: Reinforcement learning for markov exchange economy. Z Liu, M Lu, Z Wang, M Jordan, Z Yang.