Zobrazeno 1 - 10
of 82
pro vyhledávání: '"Wang, Tonghan"'
Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (
Externí odkaz:
http://arxiv.org/abs/2408.05686
Contracts are the economic framework which allows a principal to delegate a task to an agent -- despite misaligned interests, and even without directly observing the agent's actions. In many modern reinforcement learning settings, self-interested age
Externí odkaz:
http://arxiv.org/abs/2407.18074
Differentiable economics uses deep learning for automated mechanism design. Despite strong progress, it has remained an open problem to learn multi-bidder, general, and fully strategy-proof (SP) auctions. We introduce GEneral Menu-based NETwork (GemN
Externí odkaz:
http://arxiv.org/abs/2406.07428
Autor:
Zhang, Edwin, Zhao, Sadie, Wang, Tonghan, Hossain, Safwan, Gasztowtt, Henry, Zheng, Stephan, Parkes, David C., Tambe, Milind, Chen, Yiling
Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducing Social Environment Design, a general framework for
Externí odkaz:
http://arxiv.org/abs/2402.14090
We consider the multi-sender persuasion problem: multiple players with informational advantage signal to convince a single self-interested actor to take certain actions. This problem generalizes the seminal Bayesian Persuasion framework and is ubiqui
Externí odkaz:
http://arxiv.org/abs/2402.04971
In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration. While the computation of many intrinsic rewards relies on estimating variational posteriors using neural network approximators,
Externí odkaz:
http://arxiv.org/abs/2308.09909
Publikováno v:
NeurIPS 2023
Contract design involves a principal who establishes contractual agreements about payments for outcomes that arise from the actions of an agent. In this paper, we initiate the study of deep learning for the automated design of optimal contracts. We i
Externí odkaz:
http://arxiv.org/abs/2307.02318
Robot design aims at learning to create robots that can be easily controlled and perform tasks efficiently. Previous works on robot design have proven its ability to generate robots for various tasks. However, these works searched the robots directly
Externí odkaz:
http://arxiv.org/abs/2306.00036
Publikováno v:
NeurIPS 2022
Value decomposition multi-agent reinforcement learning methods learn the global value function as a mixing of each agent's individual utility functions. Coordination graphs (CGs) represent a higher-order decomposition by incorporating pairwise payoff
Externí odkaz:
http://arxiv.org/abs/2211.08404
Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator. Previous work on modular RL has proven its ability to control morphologically different agents with a shared actuator policy.
Externí odkaz:
http://arxiv.org/abs/2210.15479