Mobiltiy Aware Deep Q-Reinforcement Learning Model for Building Efficient Agriculture Autonomous Robots

in recent years the research has shown that modern farms may be helpful in producing the higher amount of yields along with superior quality. Moreover, this might also help in being least dependent about the labor force. Management of digital farming and site-specific precision are few solutions, which depends on the sensor technology. Moreover, the field data collection is the best only with feasible utilization of agriculture robots (AR). For improving agriculture productivity the sensor are placed across land (geographically), these sensor sends information to multiple robots for carrying certain task such as soughing, harvesting etc. This manuscript conducted survey of various industrial robots model for agriculture environment. Using industrial robots for agricultural purpose is practically not a viable option due to complex environment. Cognitive architecture that exhibits human cognitive thinking is used for learning dynamic and complex environment with good result. In recent times, Society of Mind Cognitive Architecture (SMCA) has proposed using multi-agent and (MA) and Reinforcement learning (RL) technique. However, it is generally difficult to solve Markov decision process (MDP) problem. Thus, cannot be used under dynamic mobility and complex nature of agriculture environment. This is because MDP has many variables. For overcoming research issues, this work present mobility aware Deep Q- Reinforcement Learning (MADQRL) cognitive learning method for Society of Mind Cognitive Architecture by combining both RL and DL technique. The MADQRL are utilized for controlling mobility and communication power of robots according to dynamic environment prerequisite. Experiment outcome shows the proposed MADQRL method attain better performance than existing cognitive learning method considering memory efficiency, learning efficiency, and energy utilization.

A Decision Making Method Based on Society of Mind Theory in Multi-Player Imperfect Information Games

The authors are concerned with a card game called Daihinmin (Extreme Needy), which is a multi-player imperfect information game. Using Marvin Minsky's “Society of Mind” theory, they attempt to model the workings of the minds of game players. The UEC Computer Daihinmin Competitions (UECda) have been held at the University of Electro-Communications since 2006, to bring together competitive client programs that correspond to players of Daihinmin, and contest their strengths. In this paper, the authors extract the behavior of client programs from actual competition records of the computer Daihinmin, and propose a method of building a system that determines the parameters of Daihinmin agencies by machine learning.

Society of Agents

The development of multiple agent systems faces many challenges, including agent coordination and collaboration on tasks. Minsky's The Society of Mind provides a conceptual view for addressing these multi-agent system problems. A new classification ontology is introduced for comparing multi-agent systems. Next, a new framework called the Society of Agents is developed from Minsky's conceptual foundation. A Society of Agents framework-based problem-solving and a Game Society is developed and applied to the domain of single player logic puzzles and two player games. The Game Society solved 100% of presented Sudoku and Kakuro problems and never lost a tic-tac-toe game. The advantage of the Society of Agents approach is the efficient re-utilization of agents across multiple independent game domain problems and a centralized problem-solving architecture with efficient cross-agent information sharing.

Selfless Minds

This chapter looks at Marvin Minsky's and Seymour Papert's recent proposal to study the mind as a society, which takes the patchwork architecture of cognition as a central element. Minsky and Papert present a view in which minds consist of many “agents” whose abilities are quite circumscribed: each agent taken individually operates only in a microworld of small-scale or “toy” problems. This model of the mind as a society of numerous agents is intended to encompass a multiplicity of approaches to the study of cognition, ranging from distributed, self-organizing networks to the classical, cognitivist conception of localized, serial symbolic processing. The society of mind purports to be, then, something of a middle way in present cognitive science. This middle way challenges a homogenous model of the mind, whether in the form of distributed networks at one extreme or symbolic processers at the other extreme.

A Decision Making Method Based on Society of Mind Theory in Multi-Player Imperfect Information Games

The authors are concerned with a card game called Daihinmin (Extreme Needy), which is a multi-player imperfect information game. Using Marvin Minsky's “Society of Mind” theory, they attempt to model the workings of the minds of game players. The UEC Computer Daihinmin Competitions (UECda) have been held at the University of Electro-Communications since 2006, to bring together competitive client programs that correspond to players of Daihinmin, and contest their strengths. In this paper, the authors extract the behavior of client programs from actual competition records of the computer Daihinmin, and propose a method of building a system that determines the parameters of Daihinmin agencies by machine learning.