Knowledge-based multiagent credit assignment: A study on task type and critic information

A Harati, MN Ahmadabadi, BN Araabi - IEEE systems journal, 2007 - ieeexplore.ieee.org
Multiagent credit assignment (MCA) is one of the major problems in the realization of
multiagent reinforcement learning. Since the environment usually is not intelligent enough to …

Experimental analysis of knowledge based multiagent credit assignment

A Harati, MN Ahmadabadi - Neural Information Processing: Research and …, 2004 - Springer
Abstract Multiagent Credit Assignment is one the major problems in realization of multi-
agent reinforcement learning. Since the environment usually is not intelligent enough to …

A new approach to credit assignment in a team of cooperative Q-learning agents

A Harati, MN Ahmadabadi - IEEE International Conference on …, 2002 - ieeexplore.ieee.org
Q-learning is widely used in many multi agent systems. In most cases, a separate critic is
considered for qualifying each individual agent behavior or it is assumed that the critic is …

[BOOK][B] Multiagent credit assignment in a team of cooperative q-learning agents with a parallel task

A Harati, MRN Ahmadabadi - 2002 - Citeseer
Traditionally in many multiagent reinforcement learning researches, qualifying each
individual agent's behavior is responsibility of environment's critic. However, in most …

Certainty and expertness-based credit assignment for cooperative Q-Learning agents with an AND-type task

A Harati, MN Ahmadabadi - Proceedings of the 9th …, 2002 - ieeexplore.ieee.org
In multiagent reinforcement learning, inter-agent credit assignment is a fundamental
problem, since a single scalar reinforcement signal is the only reliable feedback that teams …

[PDF][PDF] Certainty and Expertness–Based Credit Assignment for Cooperative Q-learning Agents with an and–Type Task

R Zaliamin, ME Shiri - Australian Journal of Basic and Applied …, 2010 - academia.edu
In mulitagent reinforcement learning, inter agent credit assignment is a fundamental
problem, since a single scalar reinforcement signal is the only reliable feedback that teams …

Learning distributed grasp in presence of redundant agents

AH Elahibakhsh, MN Ahmadabadi… - … , 2005 IEEE/ASME …, 2005 - ieeexplore.ieee.org
Learning distributed object grasp by a group of robots with redundant members is the main
focus of this paper. In Elahibakhsh, AH, et al.(2004), we tackled the problem of learning form …