Multi-agent Reinforcement Learning: An Overview

By Lucian Busoniu, Robert Babuška, B. Schutter. 2010

788 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Management Information Systems, Management Science and Operations Research, 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 Management Information Systems

In Management Science and Operations Research

In Reinforcement Learning

Citations in the corpus

Learning World Graphs to Accelerate Hierarchical Reinforcement Learning (2019, neutral): “, multi-tasking RL [42], structured exploration by using pivotal state as checkouts [25] or in multiagent settings [15, 45].”
Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, methodology): “ramework becomes inadequate when multiple autonomous agents act simultaneously in the same domain. Instead, the more general stochastic game (SG) may be used in the case of a Multi-Agent System (MAS) [54]. A SG is deﬁned as a tuple ˙ S ,A1...N T R1...N ¨, where N is the number of agents, S is the se”
Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability (2017, background): “2010) present a taxonomy of MARL approaches.”
Actor-Attention-Critic for Multi-Agent Reinforcement Learning (2018, background): “Multi-Agent Reinforcement Learning (MARL) is a long studied problem (Bus¸oniu et al., 2010).”
Negative Update Intervals in Deep Multi-Agent Reinforcement Learning (2018, background): “Thus, team games are fully cooperative settings, where players have a shared objective to maximize their common return (see Figure 1) [2, 3, 16].”
Lenient Multi-Agent Deep Reinforcement Learning (2017, methodology): “The layout in sub-figure 2a is a larger version of the original layout [6], while the layout in sub-figure 2b introduces narrow-passages between the goods and the drop-zone, testing whether the agents can learn to coordinate in order to overcome challenging areas within the environment.”
A survey and critique of multiagent deep reinforcement learning (2018, background): “This article contributes to the state of the art with a brief survey of the current works in MDRL in an effort to complement existing surveys on multiagent learning [56,141], cooperative learning [213,248], agents modeling agents [6], knowledge reuse in multiagent RL [290], and (single-agent) deep r”
Cooperative and Distributed Reinforcement Learning of Drones for Field Coverage (2018, background): “This particularly benefits the system when new agents are introduced, or the environment is changed [18].”
CESMA: Centralized Expert Supervises Multi-Agents (2019, methodology): “This was applied in [46], but this training method gives stability issues, as the environment is non-stationary from the perspective of each agent [23, 3, 4].”
Influencing Long-Term Behavior in Multiagent Reinforcement Learning (2022, neutral): “Learning in multiagent reinforcement learning (MARL) is fundamentally difficult because an agent interacts with other simultaneously learning agents in a shared environment (Bus¸oniu et al., 2010).”
Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning (2020, background): “Jiang & Lu [8] and Das et al. [9] both proposed attention based communication protocol to exchange messages in MARL domains [8], [9], but these approaches did not consider agents’ behavior knowledge.”
Provable Self-Play Algorithms for Competitive Reinforcement Learning (2020, result): “We refer the readers to several recent surveys for these results (see e.g. Bus¸oniu et al., 2010; Nguyen et al., 2018; OroojlooyJadid and Hajinezhad, 2019; Zhang et al., 2019).”
A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning (2020, background): “Learning in multiagent settings is inherently more difficult than single-agent learning because an agent interacts both with the environment and other agents (Buşoniu et al., 2010).”
Policy invariance under reward transformations for multi-objective reinforcement learning (2017, methodology): “Instead, the more general Stochastic Game (SG) may be used in the case of a MAS [18].”
Reinforcement Learning in non-stationary environments: An intrinsically motivated stress based memory retrieval performance (SBMRP) model (2014, methodology): “This simulation environment was adopted from Busoniu’s Multi Agent RL (MARL) Matlab toolbox [17].”
PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning (2018, background): “The first and most important problem encountered when transitioning from single- to multi-agent learning is the curse of dimensionality: most joint approaches fail as the stateaction spaces explode combinatorially, requiring impractical amounts of training data to converge [24].”