Deep contract design via discontinuous networks

T Wang, P Duetting, D Ivanov… - Advances in …, 2024 - proceedings.neurips.cc
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 …

Towards a better understanding of learning with multiagent teams

D Radke, K Larson, T Brecht, K Tilbury - arXiv preprint arXiv:2306.16205, 2023 - arxiv.org
While it has long been recognized that a team of individual learning agents can be greater
than the sum of its parts, recent work has shown that larger teams are not necessarily more …

The bandit whisperer: Communication learning for restless bandits

Y Zhao, T Wang, D Nagaraj, A Taneja… - arXiv preprint arXiv …, 2024 - arxiv.org
Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a
promising avenue for addressing allocation problems with resource constraints and …

Learning Optimal" Pigovian Tax" in Sequential Social Dilemmas

Y Hua, S Gao, W Li, B Jin, X Wang, H Zha - arXiv preprint arXiv …, 2023 - arxiv.org
In multi-agent reinforcement learning, each agent acts to maximize its individual
accumulated rewards. Nevertheless, individual accumulated rewards could not fully reflect …

Learning roles with emergent social value orientations

W Li, X Wang, B Jin, J Lu, H Zha - arXiv preprint arXiv:2301.13812, 2023 - arxiv.org
Social dilemmas can be considered situations where individual rationality leads to collective
irrationality. The multi-agent reinforcement learning community has leveraged ideas from …

GHQ: grouped hybrid Q-learning for cooperative heterogeneous multi-agent reinforcement learning

X Yu, Y Lin, X Wang, S Han, K Lv - Complex & Intelligent Systems, 2024 - Springer
Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved
impressive results, typically in symmetric and homogeneous scenarios. However …

GHQ: Grouped Hybrid Q Learning for Heterogeneous Cooperative Multi-agent Reinforcement Learning

X Yu, Y Lin, X Wang, S Han, K Lv - arXiv preprint arXiv:2303.01070, 2023 - arxiv.org
Previous deep multi-agent reinforcement learning (MARL) algorithms have achieved
impressive results, typically in homogeneous scenarios. However, heterogeneous scenarios …