A Comprehensive Survey of Multiagent Reinforcement Learning

By Lucian Busoniu, Robert Babuška, B. Schutter. 2008

2,254 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Reinforcement Learning

Citations in the corpus

Counterfactual Multi-Agent Policy Gradients (2017, background): “Although multi-agent RL has been applied in a variety of settings (Busoniu et al., 2008; Yang & Gu, 2004), it has often been restricted to tabular methods and simple environments.”
Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2020, background): “Recent work in multi-agent RL has started moving from tabular methods (Yang and Gu, 2004; Busoniu et al., 2008) to deep learning methods that can tackle high-dimensional state and action spaces (Tampuu et al., 2017; Foerster et al., 2018; Peng et al., 2017; de Witt et al., 2018).”
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.”
Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication (2020, neutral): “clusions and possible areas of future work in Section 6. 2 Related Work MARL has beneted from recent developments in deep reinforcement learning, with the frameworks moving away from tabular methods [2] to end-to-end schemes [7]. Our work is related to recent advances in deep multi-agent reinforceme”
Reinforcement Learning in Healthcare: A Survey (2019, background): “uot; if a= argmax a0Q(s;a), " otherwise. (7) where "2[0;1] is an exploration rate. Other fundamental issues in RL research include but are not limited to the credit assignment problem [14], [27], the sampel/space/time complexity [28], [29], function approximation [30], [31], safety [32], [”
Learning Multi-Arm Manipulation Through Collaborative Teleoperation (2020, background): “Multi-Agent Imitation Learning: Most work in Multi-Agent Imitation Learning [4, 19, 32, 33] focuses on the paradigm of Inverse Reinforcement Learning [1, 2], in which multi-agent demonstrations are used to infer a reward function, and the reward function is optimized via Reinforcement Learning (RL).”
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (2017, background): “See [26, 4] for surveys of multi-agent learning approaches and applications.”
Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games (2017, background): “s. The bi-directional nature means that the communication is not entirely symmetric, and the different priority among agents would help solving any possible tie between multiple optimal joint actions [35, 36]. 2Trademark of Blizzard EntertainmentTM. 2 Attention Neron Bi-directional RNN Policy Action”
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (2017, background): “Multi-agent RL has a rich history (Busoniu et al., 2008; Yang & Gu, 2004) but has mostly focused on tabular settings and simple environments.”
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks (2016, background): “Multi-agent reinforcement learning has been an active area of research (see e.g., [4]).”
Learning Multiagent Communication with Backpropagation (2016, background): “There is a rich literature on multi-agent reinforcement learning (MARL) [2], particularly in the robotics domain [18, 26, 6, 21, 3].”
Multi-agent reinforcement learning as a rehearsal for decentralized planning (2016, neutral): “The key difficulty of reinforcement learning in a concurrent setting is that it induces a moving target problem—the changing behavior of one agent impacts the target model that another agent wants to learn—and this has been repeatedly acknowledged in the literature [9].”
Multiagent cooperation and competition with deep reinforcement learning (2015, background): “Thus, the value of an agent’s action depends also on the actions of the others and hence each agent must keep track of each of the other learning agents, possibly resulting in an ever-moving target [3, 5, 6].”
Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge? (2020, methodology): “M ed ia n Te st W in % 6h vs 8z IPPO [2] QMIX [5] IQL [4]”
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].”
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (2018, background): “Recent work in multi-agent RL has started moving from tabular methods (Yang & Gu, 2004; Busoniu et al., 2008) to deep learning methods that can tackle high-dimensional state and action spaces (Tampuu et al., 2017; Foerster et al., 2018; Peng et al., 2017).”
Learning with Opponent-Learning Awareness (2017, background): “For further details we refer the reader to excellent reviews on the subject [6, 19].”
MAVEN: Multi-Agent Variational Exploration (2019, background): “In recent years there has been considerable work extending MARL from small discrete state spaces that can be handled by tabular methods [51, 5] to high-dimensional, continuous state spaces that require the use of function approximators [13, 28, 39].”
From Few to More: Large-scale Dynamic Multiagent Curriculum Learning (2019, background): “(Claus and Boutilier 1998; Busoniu, Babuska, and Schutter 2008).”
Action Semantics Network: Considering the Effects of Actions in Multiagent Systems (2019, background): “However, there also exist a lot of challenges in multiagent systems (MASs) since agents’ behaviors are influenced by each other and the environment exhibits more stochasticity and uncertainties (Claus & Boutilier, 1998; Hu & Wellman, 1998; Bu et al., 2008; Hauwere et al., 2016).”