Sharif Digital Repository

In multi-agent systems (MAS), collective behavior of autonomous agents and complexities arisen by their interactions are studied, while they are exploited to solve real-world complex problems. Machine learning methods are frequently used for problem solving in MAS, because complexities in these systems prevent a programmer to thoroughly describe the agents’ behaviors and the rules governing them.Reinforcement learning (RL) is one of the most commonly used learning methods for intelligent agents,because it does not need a model of the environment and learns agents’ policies through trial and error.Conventional RL algorithms store and update utilities for every possible state in a table. One... 

Schizophrenia is a devastating disorder that steals the opportunity of having a normal life from the sufferers. Drugs used in treating this disorder usually target psychotic symptoms and do not affect negative symptoms effectively. One of the deficits falling into this category is the impaired reversal learning. These patients usually learn the rules but do not renounce them after the contingencies of reward have been reversed. To investigate the reasons of this impairment, first a hypothesis of how different parts of the brain communicate during reversal learning is proposed using the physiological evidence. Then considering the known relation between the actor-critic model of the... 

The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W. R. Thompson, dates back to 1933. This algorithm,referred to as Thompson Sampling, is a natural Bayesian algorithm. The basic idea is to choose an arm to play according to its probability of being the best arm. Thompson Sampling algorithm has experimentally been shown to be close to optimal. In this dissertation several papers are being reviewed. In these papers it has been shown that Thompson Sampling algorithm achieves logarithmic expected regret for the... 

Reinforcement learning is a successful model of learning that has received a lot of attention in recent years and has had significant achievements. However, methods based on reinforcement require a lot of data. Therefore, it is important to find ideas to keep learning at a high level despite the lack of data. Many of these ideas are known as statistical regularity. In this thesis, we study methods to enhance the learning rate, including methods for sharing neural network weights between value function and policy networks. In this thesis we will try to gain a more general understanding of the regularization in reinforcement learning and increase the learning rate by implementing these methods...