Centralized model and exploration policy for multi-agent RL
Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings
(Dec-POMDPs) can in principle be used to address many real-world challenges such as …
(Dec-POMDPs) can in principle be used to address many real-world challenges such as …
Bayesian multi-type mean field multi-agent imitation learning
F Yang, A Vereshchaka, C Chen… - Advances in Neural …, 2020 - proceedings.neurips.cc
Multi-agent Imitation learning (MAIL) refers to the problem that agents learn to perform a task
interactively in a multi-agent system through observing and mimicking expert …
interactively in a multi-agent system through observing and mimicking expert …
Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning
This paper concerns imitation learning (IL)(ie, the problem of learning to mimic expert
behaviors from demonstrations) in cooperative multi-agent systems. The learning problem …
behaviors from demonstrations) in cooperative multi-agent systems. The learning problem …
Correlated Mean Field Imitation Learning
Z Zhao, N Yang, X Yan, H Zhang, J Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
We investigate multi-agent imitation learning (IL) within the framework of mean field games
(MFGs), considering the presence of time-varying correlated signals. Existing MFG IL …
(MFGs), considering the presence of time-varying correlated signals. Existing MFG IL …
Learning to Advise and Learning from Advice in Cooperative Multi-Agent Reinforcement Learning
Learning to coordinate is a daunting problem in multi-agent reinforcement learning (MARL).
Previous works have explored it from many facets, including cognition between agents …
Previous works have explored it from many facets, including cognition between agents …
Imitation Learning for Mean Field Games with Correlated Equilibria
Imitation learning (IL) is a powerful approach for acquiring optimal policies from
demonstrated behaviors. However, applying IL to a large group of agents is arduous due to …
demonstrated behaviors. However, applying IL to a large group of agents is arduous due to …
Optimal Control for Decision-Making in Single and Multi-Agent Systems
A Vereshchaka - 2021 - search.proquest.com
We live in a world full of complex interactions between agents, in which each agent carries
its own model and objective. Social-behavioural systems can be modeled as collections of …
its own model and objective. Social-behavioural systems can be modeled as collections of …
[图书][B] Reinforcement Learning and Optimal Control in Complex Social Systems
F Yang - 2020 - search.proquest.com
Complex social systems are composed of interconnected individuals whose interactions
result in group behaviors. Sequential decision making in a real-world complex system has …
result in group behaviors. Sequential decision making in a real-world complex system has …
[PDF][PDF] 軌跡に基づくエージェント固有の行動則とインセンティブの推定
浪越圭一 - (No Title), 2021 - opac.ll.chiba-u.jp
近年, 自律ロボットや自動運転車といった人工物の社会実装が進む中で, 望ましい流れを実現する
ために, 人の振舞いを予測し, 必要に応じて人や他の人工物を制御する方法が求められている …
ために, 人の振舞いを予測し, 必要に応じて人や他の人工物を制御する方法が求められている …