Multiagent Systems: A Survey from a Machine Learning Perspective

By Peter Stone, Manuela M. Veloso. 2000

1,518 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Mechanical Engineering, Reinforcement Learning, Game & Decision Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Mechanical Engineering

In Reinforcement Learning

In Game & Decision Theory

Citations in the corpus

QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning (2019, methodology): “Modified predator-prey (MPP) We adopt a more complicated environment by modifying the well-known predator- prey (Stone & Veloso, 2000) in the grid world, used in many other MARL research.”
Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery (2019, background): “archical MARL in discrete state spaces with hand-crafted subtasks [12, 22] showed that learning cooperation at the level of subtasks significantly speeds up learning over flat methods [20, 35, 39].”
Multiagent Learning: Basics, Challenges, and Prospects (2012, background): “At the end of this startup phase the first general understanding of the role of learning in multiagent settings emerged, for example, Stone and Veloso (2000) and the first textbooklike treat-ment of MAL became available (Sen and Weiss 1999).”
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “Adopting a decentralized point of view offers several potential advantages such as speed-up, scalability and robustness (Stone & Veloso, 2000).”
Supervision via competition: Robot adversaries for learning tasks (2016, background): “Multi-agent systems [27], [28] are often formulated as a cooperative game.”
Learning to Schedule Communication in Multi-agent Reinforcement Learning (2019, methodology): “Predator and prey We assess SchedNet in this predator-prey setting as in Stone & Veloso (2000), illustrated in Figure 7a.”
Coordinated Multi-Agent Imitation Learning (2017, background): “From the learning perspective, (cooperative) multi-agent learning is not a new area of research (Stone & Veloso, 2000; Panait & Luke, 2005).”
A Multiagent Approach to Autonomous Intersection Management (2008, background): “Countless films and stories have been made that focus on a future filled with such humanoid agents which, when not violently overthrowing their human masters, run errands, complete menial tasks, or perform duties that would be too difficult or dangerous for humans.”
Deep Reinforcement Learning (2023, neutral): “MARL has been used to solve a variety of issues, including robotic soccer [31], traffic management [32], and supply chain optimization [33].”
A knowledge plane for the internet (2003, background): “The field of MultiAgent Systems [22] has had some initial success in solving these problems, although those addressed to date typically lack the dynamicity required for the knowledge plane.”
New Criteria and a New Algorithm for Learning in Multi-Agent Systems (2004, background): “There is a growing body of algorithms proposed, and some arguments about their relative merits and domains of applicability (for example, [14] and [17]).”
Making friends on the fly: Cooperating with new teammates (2017, positive): “The pursuit domain, also known as the predator-prey domain, is a popular problem in multiagent systems literature as it requires cooperation between all of the teammates to capture the prey while remaining simple enough to evaluate approaches well [66].”
Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation (2016, methodology): “In this paper, we use an end-to-end framework to learn a collision-avoidance policy which is robust to the imperfect sensing and requires no inter-agent communication, and thus is still fully distributed.”
A Roadmap of Agent Research and Development (2004, background): “Another important aspect of successful interaction for self-interested agents is the ability to adapt behaviour to changing circumstances (see [138] for a survey).”
Multiagent traffic management: a reservation-based intersection control mechanism (2004, background): “systems involving multiple agents and mechanisms for coordination of independent agents’ behaviors [9].”
CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning (2018, background): “While the framework of multi-agent reinforcement learning (MARL) [40, 17, 35, 9, 30] has been equipped with successful methods in deep reinforcement learning (RL) [20, 15] and shown promise on high-dimensional problems with complex agent interactions [19, 21, 13, 6, 16, 34], learning multi-agent coo”
A review of cooperative multi-agent deep reinforcement learning (2019, background): “en features from the individual value-based network to help sample efﬁciency. Intheexperimentalanalysis,thecomparisonsofQTRANwithVDNandQMIXonMulti-domainGaussian Squeeze [47] and modiﬁed predator-prey[127] is provided. Within the cooperative setting with the absence of joint reward, the reward-shapi”