Multi-agent learning via markov potential games in marketplaces for distributed energy resources
D Narasimha, K Lee, D Kalathil… - 2022 IEEE 61st …, 2022 - ieeexplore.ieee.org
Much change is happening in electricity markets due to the entrance of small-scale
prosumers that both generate and consume electricity. Both large and small consumers can …
prosumers that both generate and consume electricity. Both large and small consumers can …
Finite-sample analysis of decentralized Q-learning for stochastic games
Learning in stochastic games is arguably the most standard and fundamental setting in multi-
agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in …
agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in …
[PDF][PDF] Aarhus University
B Hansen, SC Sølvsten - arXiv preprint arXiv:2006.08314, 2020 - ask.qcloudimg.com
We show that the problem of deciding whether in a multi-player perfect information recursive
game (ie a stochastic game with terminal rewards) there exists a stationary Nash equilibrium …
game (ie a stochastic game with terminal rewards) there exists a stationary Nash equilibrium …
Sample complexity of decentralized tabular Q-learning for stochastic games
In this paper, we carry out finite-sample analysis of decentralized Q-learning algorithms in
the tabular setting for a significant subclass of general-sum stochastic games (SGs)–weakly …
the tabular setting for a significant subclass of general-sum stochastic games (SGs)–weakly …
Rational verification with quantitative probabilistic goals
D Hyland, K Shankaranarayanan… - International …, 2024 - research.monash.edu
We study the rational verification problem for multi-agent systems in a setting where agents
have quantitative probabilistic goals. We use concurrent stochastic games to model multi …
have quantitative probabilistic goals. We use concurrent stochastic games to model multi …
Answerable and unanswerable questions in risk analysis with open‐world novelty
LA Cox Jr - Risk Analysis, 2020 - Wiley Online Library
Decision analysis and risk analysis have grown up around a set of organizing questions:
what might go wrong, how likely is it to do so, how bad might the consequences be, what …
what might go wrong, how likely is it to do so, how bad might the consequences be, what …
[PDF][PDF] The University of Chicago
G Gao - United States, 2023 - knowledge.uchicago.edu
4 DESIGN OF POWER PURCHASE AGREEMENTS WITH RENEWABLE ENERGY
GENERATORS................................ 243 4.1 Introduction.................................... 243 4.1. 1 …
GENERATORS................................ 243 4.1 Introduction.................................... 243 4.1. 1 …
Stochastic equilibria under imprecise deviations in terminal-reward concurrent games
We study the existence of mixed-strategy equilibria in concurrent games played on graphs.
While existence is guaranteed with safety objectives for each player, Nash equilibria need …
While existence is guaranteed with safety objectives for each player, Nash equilibria need …
Answerable and Unanswerable Questions in Decision and Risk Analysis
LA Cox Jr - AI-ML for Decision and Risk Analysis: Challenges and …, 2023 - Springer
Decision analysis and risk analysis have grown up around a set of organizing questions:
what might go wrong, how likely is it to do so, how bad might the consequences be, what …
what might go wrong, how likely is it to do so, how bad might the consequences be, what …
Existential theory of the reals completeness of stationary nash equilibria in perfect information stochastic games
KA Hansen, SC Sølvsten - arXiv preprint arXiv:2006.08314, 2020 - arxiv.org
We show that the problem of deciding whether in a multi-player perfect information recursive
game (ie a stochastic game with terminal rewards) there exists a stationary Nash equilibrium …
game (ie a stochastic game with terminal rewards) there exists a stationary Nash equilibrium …