Majid Nili Ahmadabadi

Position: 
Professor
Phone Number: 
+98 21 6111 4221
E-Mail: 
mnili@ut.ac.ir
Research Interests Keywords: 
---
Projects: 
Intelligent toys
Industrial robot controller
Publications: 
Manipulation of polygonal objects with two wheeled-tip fingers: Planning in the presence of contact position error
Expertness based cooperative Q-learning
Cooperative Q-learning: the knowledge sharing issue
Heterogeneous and Hierarchical Cooperative Learning via Combining Decision Trees
Knowledge-based Extraction of Area of Expertise for Cooperation in Learning
Reduction of Learning Time for Robots Using Automatic State Abstraction
Expertness measuring in cooperative learning
Learning with which Local Decision Expert to Consult Next Case Study: Arrhythmia Diagnosis
A Wheel Based Climbing Robot: Modeling and Control
Attention Control with Reinforcement Learning for Face Recognition under Partial Occlusion
A New Probabilistic Method for Petroleum Reservoir Production Prediction and History Matching
Online Learning of Task-driven Object-based Visual Attention Control
Exploration and exploitation balance management in fuzzy reinforcement learning
A Behavioral Approach to Estimate Area of Expertise for Cooperative Q-Learning: A Self Referenced Strategy
Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition
Fuzzy Sarsa Learning and the Proof of Existence of its Stationary Points
A study on effects of reward distribution on learning of a team of distributed agents
Weighted Strategy Sharing: A New Multi-Agent Cooperative Learning Method Based on Expertness Measuring
An expert system design for a crude oil distillation column with Neural Networks model and the process optimization using genetic algorithm framework
Knowledge-Based Multiagent Credit Assignment: A Study on Task Type and Critic Information
A Study on Expertise of Agents and Its Effect on Cooperative Q-learning
Dynamic Object Manipulation Using an Array of 1-DOF Arms: Kinematical Modeling and Planning
A cooperative learning approach to Mixed Performance Controller design: a behavioral viewpoint
A Study on the Role of Exploration in Multiagent Reinforcement Learning Considering Task Type
Swarm Contours: A Fast Self-Organization Approach for Snake Initialization
Development and Modeling of a Differential-drive-based Holonomic Mobile Robot
Distributed Object Transportation on a Desired Path Based on Constrain-and-Move Strategy
Distributed Cooperative Load Redistribution for Fault Tolerance in a Team of four Object Lifting Robots
Improving Gyro-Odometery for Mobile Robot Localization
Compliance: Encoded information and behavior in a team of cooperative object handling robots
Compliance: Encoded information and behavior in a team of cooperative object handling robots
Expertness Based Cooperative Q‑Learning
Cooperative Q‑learning: The Knowledge Sharing Issue
A Constrain and move approach to distributed object Manipulation
Extending Constrain-Move Based Cooperation Strategy for Four Object Lifting Robots
Behavior study of a Combination of FLC and GA Controlling a Robot Arm Along a Desired Trajectory
Learning Cluster Type and Dissimilarity Metric for each Cluster using a Set of Possible Cluster Types
Cost-sensitive learning of top-down modulation for attentional control
Learning Active Fusion of Multiple Experts' Decisions: An Attention-based Approach
METAL: A Framework for Mixture-of-Experts Task and Attention Learning
Analogy between Juggling and Hopping: Active object manipulation approach
Interaction of Culture-based Learning and Cooperative Co-evolution and its Application to Automatic Behavior-based System Design