Decentralized POMDPs

By Frans Adriaan Oliehoek. 2012

161 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Management Information Systems, 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 Control and Systems Engineering

In Management Information Systems

In Management Science and Operations Research

Citations in the corpus

Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning (2019, background): “In this paper we assume a Dec-POMDP (Oliehoek, 2012), in which N agents interact in a partially observable environment.”
Guided Deep Reinforcement Learning for Swarm Systems (2017, methodology): “We formulate the swarm system as a swarm MDP (see [16] for a similar definition) which can be seen as a special case of a decentralized partially observed Markov decision process (Dec-POMDP) [12].”
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning (2018, background): “This setting can be formalised as a Dec-POMDP (Oliehoek, 2012).”
Inverse Reinforcement Learning in Swarm Systems (2016, background): “belief state policies [11] or such that operate on observation histories [21]) is straightforward.”
A Concise Introduction to Decentralized POMDPs (2016, background): “In particular, many parts were based on the authors’ previous theses, book chapters and survey articles [Oliehoek, 2010, 2012, Amato, 2010, 2015, Amato et al., 2013].”
Learning for Decentralized Control of Multiagent Systems in Large, Partially-Observable Stochastic Environments (2016, background): “This SAR problem, in its most general form, can be formulated as a decentralized partially observable Markov decision process (Dec-POMDP) (Oliehoek 2012; Amato et al. 2013), where a team of agents must cooperate to optimize some global objective in the presence of uncertainty.”
TCP ex machina: computer-generated congestion control (2013, methodology): “Formally, we treat the problem of finding the best RemyCC under uncertain network conditions as a search for the best policy for a decentralized partially-observable Markov decision process, or DecPOMDP [34].”
Multi-Agent Connected Autonomous Driving using Deep Reinforcement Learning (2019, background): “The particular case in which all the agents acting in a partially observable environment share the same reward function, can be studied under the DEC-POMDP [19] formulation.”
Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications (2018, methodology): “The agents are not explicitly provided with task identity (thus partial observability) while they cooperatively learn to complete a set of decentralized POMDP tasks with sparse rewards.”
Local Communication Protocols for Learning Complex Swarm Behaviors with Deep Reinforcement Learning (2017, unknown): “partially observed Markov decision process (Dec-POMDP) [20].”
Scalable Planning and Learning for Multiagent POMDPs (2014, methodology): “Locality of interaction has also been considered previously in decentralized POMDP methods (Oliehoek, 2012; Amato et al., 2013) in the form of factored Dec-POMDPs (Oliehoek, Whiteson, and Spaan, 2013; Pa-jarinen and Peltonen, 2011) and networked distributed POMDPs (ND-POMDPs) (Nair et al., 2005;…”