Academic Journal
Parallel Fault Tolerant Multi-Agent Reinforcement Learning
| العنوان: | Parallel Fault Tolerant Multi-Agent Reinforcement Learning |
|---|---|
| المؤلفون: | Christopher C. Johnson |
| المساهمون: | The Pennsylvania State University CiteSeerX Archives |
| المصدر: | http://www.cs.utexas.edu/%7Ecjohnson/ParallelFTRL.pdf. |
| سنة النشر: | 2011 |
| المجموعة: | CiteSeerX |
| الوصف: | Reinforcement learning is a powerful tool for training an agent in a sequential decision based environment and has been successful in many simulated [6] as well as practical [5] domains. In this paper we investigate methods of strengthening the rate of convergence of a single agent RL learner by sharing observations with other independent agents. In contrast to multi-agent reinforcement methods that investigate cooperative learning between agents using a shared policy [4], this paper is instead interested in agent’s that learn independently and share observations through periodic, asynchronous message passing. In addition to the goal of increasing optimal policy convergence, we investigate methods of fault tolerance in the parallel multi-agent RL framework where multiple adversarial agents may attempt to hinder the learning of the other agents. 1 |
| نوع الوثيقة: | text |
| وصف الملف: | application/pdf |
| اللغة: | English |
| Relation: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.2883; http://www.cs.utexas.edu/%7Ecjohnson/ParallelFTRL.pdf |
| الاتاحة: | http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.2883 http://www.cs.utexas.edu/%7Ecjohnson/ParallelFTRL.pdf |
| Rights: | Metadata may be used without restrictions as long as the oai identifier remains attached to it. |
| رقم الانضمام: | edsbas.A83BEDFB |
| قاعدة البيانات: | BASE |
| الوصف غير متاح. |