Influence-Optimistic Local Values for Multiagent Planning
نویسندگان
چکیده
Over the last decade, methods for multiagent planning under uncertainty have increased in scalability. However, many methods assume value factorization or are not able to provide quality guarantees. We propose a novel family of influence-optimistic upper bounds on the optimal value for problems with 100s of agents that do not exhibit value factorization.
منابع مشابه
Influence-Optimistic Local Values for Multiagent Planning - Extended Version
Recent years have seen the development of a number of methods for multiagent planning under uncertainty that scale to tens or even hundreds of agents. However, most of these methods either make restrictive assumptions on the problem domain, or provide approximate solutions without any guarantees on quality. To allow for meaningful benchmarking through measurable quality guarantees on a very gen...
متن کاملFactored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions
Nowadays, multiagent planning under uncertainty scales to tens or even hundreds of agents. However, current methods either are restricted to problems with factored value functions, or provide solutions without any guarantees on quality. Methods in the former category typically build on heuristic search using upper bounds on the value function. Unfortunately, no techniques exist to compute such ...
متن کاملFast Solving of Influence Diagrams for Multiagent Planning on GPU-enabled Architectures
Planning under uncertainty in multiagent settings is highly intractable because of history and plan space complexities. Probabilistic graphical models exploit the structure of the problem domain to mitigate the computational burden. In this paper, we introduce the first parallelization of planning in multiagent settings on a CPU-GPU heterogeneous system. In particular, we focus on the algorithm...
متن کاملCooperative behavior acquistion by asynchronous policy renewal that enables simultaneous learning in multiagent enviroment
This paper presents a method for simultaneous learning in multiagent environment to emerge the cooperative behaviors. Each agent has one policy and one action value function: the former is for action execution based on the the action value function updated in the previous stage, and the latter is for learning based on the episodes experienced by the 2-greedy method. This makes all agents behave...
متن کاملTopology-preserving flocking of nonlinear agents using optimistic planning
We consider the generalized flocking problem in multiagent systems, where the agents must drive a subset of their state variables to common values, while communication is constrained by a proximity relationship in terms of another subset of variables. We build a flocking method for general nonlinear agent dynamics, by using at each agent a near-optimal control technique from artificial intellig...
متن کامل