Decentralized MDPs with sparse interactions

By Francisco S. Melo, Manuela M. Veloso. 2011

108 citations recorded by the source corpus.

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

In Computer Networks and Communications

In Management Science and Operations Research

Citations in the corpus

Value Function Transfer for Deep Multi-Agent Reinforcement Learning Based on N-Step Returns (2019, methodology): “…coordination graphs, recent work focuses on automatically identifying interaction areas during the learning process and can be applied to more general learning tasks [De Hauwere et al. , 2010; Hauwere et al. , 2011; Kok et al. , 2005; Melo and Veloso, 2009; Melo and Veloso, 2011; Yu et al. , 2015].”
PRECOG: PREdiction Conditioned on Goals in Visual Multi-Agent Settings (2019, background): “These frameworks facilitate reasoning about collaboration strategies, but suffer from “state space explosion” intractability except when interactions are known to be sparse [24] or hierarchically decomposable [11].”
Multiagent Learning of Coordination in Loosely Coupled Multiagent Systems (2015, methodology): “These approaches simplify the problem by predefi ning the dangerous areas for the robots [35], [34], or by imposing ome assumptions on each robot, either its individual optimal po licy [23], or the full observability of the other robot’s state [22] and action [36].”
QD-Learning: A Collaborative Distributed Strategy for Multi-Agent Reinforcement Learning Through Consensus + Innovations (2012, background): “More specifically, at a given time instant, each agent has access to its local instantaneous one-stage cost only and not their network average; whereas (often by problem definition), the fully cooperative formulations mentioned above (see also [23] for several decentralized variants) assume that the”
Coordinated Multi-Robot Exploration Under Communication Constraints Using Decentralized Markov Decision Processes (2012, background): “Especially, one of the directions that attracts more and more from attention this community is to take advantage of local interactions and coordination with an interactionoriented (IO) resolution (Canu and Mouaddib 2011; Melo and Veloso 2011; Velagapudi et al. 2011).”
Multi-Agent Game Abstraction via Graph Attention Neural Network (2019, methodology): “…techniques such as game abstraction and knowledge transfer to help with speeding up multi-agent re-inforcement learning(Guestrin, Lagoudakis, and Parr 2002; Kok and Vlassis 2004; De Hauwere, Vrancx, and Now ´ e 2010; Melo and Veloso 2011; Hu, Gao, and An 2015; Yu et al. 2015; Liu et al. 2019).”
Planning with macro-actions in decentralized POMDPs (2014, methodology): “Other methods have considered locations or states where interaction is needed to improve scalability in planning [27, 31] and learning [20].”
Learning in Multi-agent Systems with Sparse Interactions by Knowledge Transfer and Game Abstraction (2015, methodology): “This motivates the more recent work that learns the interaction areas during the learning process [4,9,13,17,18].”
QueryPOMDP: POMDP-Based Communication in Multiagent Systems (2011, methodology): “Further examples of models with sparse interactions include interaction-driven Markov games (IDMGs) [5, 17], distributed POMDPs with coordination locales [7], transition-decoupled POMDPs [6], factored Dec-POMDPs [4], and models relying on event-driven interactions [3,27].”