Value-Based Planning for Teams of Agents in Stochastic Partially Observable Environments

2010

Citations in the corpus

• The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning (2019, neutral): “Aloha [21] is a partially observable game in which there is a set of islands, each provided with a radio station, trying to send a message to their inhabitants.”
• Decentralized POMDPs (2012, unknown): “Approximate solutions, however, were shown to scale to hundreds of agents (Oliehoek, 2010).”
• A Concise Introduction to Decentralized POMDPs (2016, unknown): “1 For a deeper treatment of the relation between MBDP and PBDP, we refer to the description by Oliehoek [2012].”
• Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games (2011, unknown): “PLUS to this factor graph formulation in order to efficiently solve CGBGs. 6In previous work, we referred to this as the ‘type-action’ factor graph, since its variables correspond to actions selected for individual types (Oliehoek, 2010).”