2LRL: a two-level multi-agent reinforcement learning algorithm with communication

Download
2002
Erus, Guray
Learning is a key element of an "intelligent" computational system. In Multi- agent Systems (MASs), learning involves acquisition of a cooperative behavior in order to satisfy the joint goals. Reinforcement Learning (RL) is a promising unsupervised machine learning technique inspired from the earlier studies in animal learning. In this thesis, we propose the Two Level Reinforcement Learning with Communication (2LRL) method, a new RL technique to provide cooperative action selection in a multi-agent environment. In 2LRL, the decision mechanism of the agents is divided into two hierarchical levels, in which the agents learn to select their target in the first level and to select the action directed to their target in the second level. The agents communicate their perception to their neighbors and use the communication information in their decision-making. We applied 2LRL method in a hunter-prey environment and observed a satisfactory cooperative behavior.

Suggestions

Recursive Compositional Reinforcement Learning for Continuous Control Sürekli Kontrol Uygulamalari için Özyinelemeli Bileşimsel Pekiştirmeli Öǧrenme
Tanik, Guven Orkun; Ertekin Bolelli, Şeyda (2022-01-01)
Compositional and temporal abstraction is the key to improving learning and planning in reinforcement learning. Modern real-world control problems call for continuous control domains and robust, sample efficient and explainable control frameworks. We are presenting a framework for recursively composing control skills to solve compositional and progressively complex tasks. The framework promotes reuse of skills, and as a result quickly adaptable to new tasks. The decision-tree can be observed, providing insi...
Intelligent learning system for online learning
Serçe, Fatma Cemile; Alpaslan, Ferda Nur; Jain, Lakhmi (2008-10-01)
The paper presents an Adaptive Intelligent Learning System (AILS) designed to be used with any Learning Management System (LMS). The adaptiveness provides uniquely identifying and monitoring the learner's learning process according to the learner's profile. AILS has been implemented as a multi-agent system. The agents were developed as JADE agents. The paper presents the learning model, system components, agent behavior in learner scenarios, the ontologies used in agent communications, and the adaptive stra...
Reinforcement Learning in Card Game Environments Using Monte Carlo Methods and Artificial Neural Networks
Baykal, Ömer; Alpaslan, Ferda Nur (2019-09-01)
Artificial intelligence has wide range of application areas and games are one of the important ones. There are many applications of artificial intelligence methods in game environments. It is very common for game environments to include intelligent agents. Having intelligent agents makes a game more entertaining and challenging for its players. Reinforcement learning methods can be applied to develop artificial intelligence agents that learn to play a game by themselves without any supervision and can play ...
Learning to play an imperfect information card game using reinforcement learning
Alpaslan, Ferda Nur; Baykal, Ömer; Demirdöver, Buğra Kaan (2022-08-01)
Artificial intelligence and machine learning are widely popular in many areas. One of the most popular ones is gaming. Games are perfect testbeds for machine learning and artificial intelligence with various scenarios and types. This study aims to develop a self-learning intelligent agent to play the Hearts game. Hearts is one of the most popular trick-taking card games around the world. It is an imperfect information card game. In addition to having a huge state space, Hearts offers many extra challenges d...
Machine Learning Models to Enhance the Science of Cognitive Autonomy
MANİ, Ganapathy; BHARGAVA, Bharat; Angın, Pelin; VİLLARREAL VASQUEZ, Miguel; ULYBYSHEV, Denis; KOBES, Jason (2018-09-28)
Intelligent Autonomous Systems (IAS) are highly cognitive, reflective, multitask-able, and effective in knowledge discovery. Examples of IAS include software systems that are capable of automatic reconfiguration, autonomous vehicles, network of sensors with reconfigurable sensory platforms, and an unmanned aerial vehicle (UAV) respecting privacy by deciding to turn off its camera when pointing inside a private residence. Research is needed to build systems that can monitor their environment and interactions...
Citation Formats
G. Erus, “2LRL: a two-level multi-agent reinforcement learning algorithm with communication,” M.S. - Master of Science, Middle East Technical University, 2002.