Reinforcement Learning for Decentralized Planning Under Uncertainty (Doctoral Consortium)

نویسنده

  • Landon Kraemer
چکیده

Decentralized partially-observable Markov decision processes (Dec-POMDPs) are a powerful tool for modeling multi-agent planning and decision-making under uncertainty. Prevalent Dec-POMDP solution techniques require centralized computation given full knowledge of the underlying model. But in real world scenarios, model parameters may not be known a priori, or may be difficult to specify. We propose to address these limitations with distributed reinforcement learning (RL).

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Adapting Plans through Communication with Unknown Teammates: (Doctoral Consortium)

Coordinating a team of autonomous agents is a challenging problem. Agents must act in such a way that makes progress toward the achievement of a goal while avoiding conflict with their teammates. In information asymmetric domains, it is often necessary to share crucial observations in order to collaborate effectively. In traditional multiagent systems literature, these teams of agents share an ...

متن کامل

Concurrent reinforcement learning as a rehearsal for decentralized planning under uncertainty

Decentralized partially-observable Markov decision processes (Dec-POMDPs) are a powerful tool for modeling multi-agent planning and decision-making under uncertainty. Prevalent Dec-POMDP solution techniques require centralized computation given full knowledge of the underlying model. Reinforcement learning (RL) based approaches have been recently proposed for distributed solution of Dec-POMDPs ...

متن کامل

Decentralized Planning for Self-Adaptation in Multi-cloud Environment

The runtime management of Internet of Things (IoT) oriented applications deployed in multi-clouds is a complex issue due to the highly heterogeneous and dynamic execution environment. To effectively cope with such an environment, the cross-layer and multi-cloud effects should be taken into account and a decentralized self-adaptation is a promising solution to maintain and evolve the application...

متن کامل

Optimizing decentralized production–distribution planning problem in a multi-period supply chain network under uncertainty

Decentralized supply chain management is found to be significantly relevant in today’s competitive markets. Production and distribution planning is posed as an important optimization problem in supply chain networks. Here, we propose a multi-period decentralized supply chain network model with uncertainty. The imprecision related to uncertain parameters like demand and price of the final produc...

متن کامل

Large-Scale Planning Under Uncertainty: A Survey

Our research area is planning under uncertainty, that is, making sequences of decisions in the face of imperfect information. We are particularly concerned with developing planning algorithms that perform well in large, real-world domains. This paper is a brief introduction to this area of research, which draws upon results from operations research (Markov decision processes), machine learning ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013