Cooperative Multi-Agent Learning: The State of the Art

By Liviu Panait, Sean Luke. 2005

1,452 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science, LLM Agents & Tool Use, Reinforcement Learning

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 Sociology and Political Science

In LLM Agents & Tool Use

In Reinforcement Learning

Citations in the corpus

Learning to Communicate with Deep Multi-Agent Reinforcement Learning (2016, background): “The rapid progress in recent years of machine learning, and deep learning in particular, opens the door to a new perspective on this debate.”
Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017, background): “We consider the cooperative multi-agent reinforcement learning (MARL) problem (Panait and Luke, 2005; Busoniu et al., 2008; Tuyls and Weiss, 2012), in which a system of several learning agents must jointly optimize a single reward signal – the team reward – accumulated over time.”
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? (2020, background): “…(MARL) has shown considerable promise in solving tasks that can be described as a Dec-POMDP [17], i.e., where agents optimise a single scalar team reward signal in a partially observable environment while choosing actions based only on their own local action-observation histories [18, 2, 29].”
The Hanabi Challenge: A New Frontier for AI Research (2019, background): “Several years of work on MARL gave rise to many algorithms, extensions, and analyses [59, 60, 61, 62, 63].”
Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks (2016, background): “There has been a plethora of work on multi-agent reinforcement learning with communication, e.g., (Tan, 1993; Melo et al., 2011; Panait & Luke, 2005; Zhang & Lesser, 2013; Maravall et al., 2013).”
Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery (2019, background): “Fully cooperative multi-agent reinforcement learning (MARL) is an active area of research [14, 25] with a diverse set of real-world application, which include autonomous navigation [6], game AI”
Mean Field Multi-Agent Reinforcement Learning (2018, background): “Studies show that an agent who learns the effect of joint actions has better performance than those who do not in many scenarios, including cooperative games (Panait & Luke, 2005), zero-sum stochastic games (Littman, 1994), and general-sum stochastic games (Littman, 2001; Hu & Wellman, 2003).”
Multiagent Learning: Basics, Challenges, and Prospects (2012, background): “For the sake of completeness, there are several recent articles available that do an excellent job on surveying MAL; see, for example, Busoniu, Babuska, and De Schutter (2008); Panait and Luke (2005); Yang and Gu (2009).”
Emergent Complexity via Multi-Agent Competition (2017, background): “A lot of the work on multi-agent RL is focused on cooperative settings, see Busoniu et al. [2008] for a review of multi-agent RL and Panait and Luke [2005] for a review focused on cooperative settings.”
Supervision via competition: Robot adversaries for learning tasks (2016, background): “Multi-agent systems [27], [28] are often formulated as a cooperative game.”
Emergent Communication through Negotiation (2018, background): “Recent work on deep multi-agent reinforcement learning (MARL) has shown great success in teaching agents complex behaviour without a complex environment simulator or demonstration data (Panait & Luke, 2005; Busoniu et al., 2008; Tuyls & Weiss, 2012; Silver et al., 2017; Leibo et al., 2017).”
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).”
Large scale evolutionary optimization using cooperative coevolution (2008, background): “In the domain of learning multiagent behaviors, CC represents a natural approach to applying traditional evolutionary computation [7,8].”
Towards Understanding Linear Value Decomposition in Cooperative Multi-Agent Q-Learning (2020, background): “Such complex tasks require MARL to learn decentralized policies for agents to jointly optimize a global cumulative reward signal, and post a number of challenges, including multi-agent credit assignment [4–6], non-stationarity [7,8], and scalability [3,9].”
Neural Replicator Dynamics (2019, background): “In multiagent reinforcement learning (MARL), agents interact in a shared environment and aim to learn policies that maximize their returns [15, 48, 62].”
Deep Co-Training for Semi-Supervised Image Recognition (2018, background): “Multi-Agent Learning After the literature review of the most recent semi-supervised learning methods for image recognition, we ﬁnd that almost all of them are within the multi-agent learning framework [49].”