Behrooz Masoumi

Learn More
Index Terms: Entropy Learning automata Markov games Multi agent systems Stigmergy a b s t r a c t Learning automata (LA) were recently shown to be valuable tools for designing Multi-Agent Reinforcement Learning algorithms and are able to control the stochastic games. In this paper, the concepts of stigmergy and entropy are imported into learning automata(More)
Markov games, as the generalization of Markov decision processes to the multi-agent case, have long been used for modeling multi-agent systems (MAS). The Markov game view of MAS is considered as a sequence of games having to be played by multiple players while each game belongs to a different state of the environment. In this paper, several learning(More)
— RoboCup Rescue Simulation System is a suitable test-bed for test and evaluation of multiagent system's related ideas and techniques. Hence, the world RoboCup competitions is hold each year and the used ideas and techniques are evaluated in the form of different teams. Almost all of participated teams in the world RoboCup competitions use the shortest path(More)
Markov games, as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi-agent systems. In this paper, several learning automata based multi-agent system algorithms for finding optimal policies in fully-cooperative Markov Games are proposed. In the proposed algorithms, Markov problem is described as a(More)
In electronic commerce markets, agents often should acquire multiple resources to fulfill a high-level task. In order to attain such resources they need to compete with each other. In multi-agent environments, in which competition is involved, negotiation would be an interaction between agents in order to reach an agreement on resource allocation and to be(More)
> @ɳ ʆɳ ʇɳɷ @ɳ @ɸ @ ɸʈ 1 = @ ɷ 2 ʇ ʀ ɷɳʀ >ɷ @ɷ ɳ @ ɷ> ɳ ʈ ɸɳ >ɳ ɳ. @ɳ @ ɸɳ ɳ @ @ɸ < @ ɷ>. ɳɷʀ ɳ ɷ> ʀ ʀ ʀ ɻ ʃ ʁɳɳ @ ɷ> ɷɷ @> @ɳ > @ɳ @ɸ >ɷ ʈ ɳ @ @ > ɷɳ ɷ >ɷ ʄ. @ʈɷ >ɸɮ <ʀ @ ɷ> >ɳ @ɳ > @ɳ ɳ ʇ>ɳ> ʆ @ɸ @> ɷ> @> ʈ ɳ > ɸɳ @ > ɸɳ Q ɷɳ> ɳ ɳ. ABSTRACT Coordination is an important issue in multi-agent systems and has been studied by many researchers. A common testbed(More)
In this paper, a new algorithm based on case base reasoning and reinforcement learning is proposed to increase the rate convergence of the reinforcement learning algorithms in multi-agent systems. In the propose method, we investigate how making improved action selection in reinforcement learning (RL) algorithm. In the proposed method, the new combined(More)
The new generations of networks are sensor networks which typically consist of a large number of nodes that are connected wirelessly. The main idea of these types of networks is collecting data around the network&apos;s sensors. Since the sensors nodes work with the battery and there is no possibility to change or recharge these batteries, the life time of(More)