Reinforcement learning for stochastic cooperative multi-agent-systems
By Martin Lauer, Martin A. Riedmiller. 2004
36 citations recorded by the source corpus.
We present a distributed variant of Q-learning that allows to learn the optimal cost-to-go function in stochastic cooperative multi-agent domains without communication between the agents.
Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research
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
- Karl Tuyls
- Julien Pérolat
- Thore Graepel
- Marc Lanctot
- Shimon Whiteson
- Jun Wang
- Sergey Levine
- Vinícius Flores Zambaldi
In Computer Networks and Communications
- Nadine Le Fort-Piat
- David Silver
- Thore Graepel
- Marc Lanctot
- Guillaume J. Laurent
- Karl Tuyls
- Laëtitia Matignon
- Vinícius Flores Zambaldi
In Management Science and Operations Research
- Karl Tuyls
- Julien Pérolat
- Nadine Le Fort-Piat
- Guillaume J. Laurent
- Laëtitia Matignon
- Thore Graepel
- Vinícius Flores Zambaldi
- Marc Lanctot
Citations in the corpus
- Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games (2017, background): “ messages passing between agents areallowed.Theagentisalsonamedasa independentlearner . The idea of learning independent agents can also be found (Lauer and Riedmiller 2000;KapetanakisandKudenko2002; Lauer and Riedmiller 2004;Foerster et al .2016). In DIAL, each agent consists of a recurrent neural ”
- Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “Lauer and Riedmiller (2004) proposed an implicit mechanism which allows ILs to distinguish between different joint actions without knowing what exactly the joint actions are.”
- A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, methodology): “Classical techniques collect or approximate extra information such as the joint values [62, 19, 29, 56],”
- The world of independent learners is not markovian (2011, methodology): “A few approaches address this by restoring the Markovian property of the local environment by the memorizing of past events [15,20].”
- Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, unknown): “Other ideas include using joint action-value function [17, 26, 49, 54] and value function factorization [27, 44, 77], addressing the variance problem by a large batch size [5], learning grounded cooperative communication protocols between agents [18, 22, 30, 40, 50, 62, 89].”