+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Effectiveness of reinforcement learning agent with the division of perception information for multi-agent environment



Effectiveness of reinforcement learning agent with the division of perception information for multi-agent environment



Bulletin of the Okayama University of Science A Natural Science (42A): 115-124



Reinforcement learning (RL) is known to be a promising technique for creating agents that can be applied to multi-agent environment in real world problems. When multi-agent RL algorithms are applied to such complex problems, the amount of perception information in the algorithms increases enormously, and the large learning times are required. In this paper, we present a technique that divides the perception information in order to reduce the learning times. We evaluate the profit sharing based reinforcement learning algorithm with the technique for the clean-up problem in the multi-agent environment. The results, show that our proposed method is effective and can adapt in the multi-agent environment in faster learning time than traditional method.

Please choose payment method:






(PDF emailed within 1 workday: $29.90)

Accession: 015646010

Download citation: RISBibTeXText


Related references

Multi-agent reinforcement learning: weighting and partitioning. Neural Networks 12(4-5): 727-753, 1999

Performance of agent using reinforcement learning in the environment containing deadlock. Bulletin of the Okayama University of Science A Natural Science (40A): 111-120, 2004

Emergence of linguistic conventions in multi-agent reinforcement learning. Plos one 13(11): E0208095, 2018

Optimal control in microgrid using multi-agent reinforcement learning. Isa Transactions 51(6): 743-751, 2012

Collaborative multi-agent reinforcement learning based on experience propagation. Journal of Systems Engineering and Electronics 24(4): 683-689, 2013

Embodied imitation-enhanced reinforcement learning in multi-agent systems. Adaptive Behavior 22(1): 31-50, 2014

Multi-agent reinforcement learning for modeling and control of thermostatically controlled loads. Applied Energy 238: 1022-1035, 2019

Multi-agent discrete-time graphical games and reinforcement learning solutions. Automatica 50(12): 3038-3053, 2014

MARL-Ped: A multi-agent reinforcement learning based framework to simulate pedestrian groups. Simulation Modelling Practice and Theory 47: 259-275, 2014

Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models. Simulation Modelling Practice and Theory 74: 117-133, 2017

Simulation and validation of a reinforcement learning agent-based model for multi-stakeholder forest management. Computers Environment and Urban Systems 34(2): 162-174, 2010

Smart generation control based on multi-agent reinforcement learning with the idea of the time tunnel. Energy 153: 977-987, 2018

A multi-agent reinforcement learning approach to obtaining dynamic control policies for stochastic lot scheduling problem. Simulation Modelling Practice and Theory 13(5): 389-406, 2005

Locus of control and the perception of freedom in an agent of reinforcement. Journal of Research in Personality 14(4): 433-444, 1980

A multi-componential analysis of emotions during complex learning with an intelligent multi-agent system. Computers in Human Behavior 48: 615-625, 2015