KF
K. Fani
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
In order to do something useful, you should know what to do and how to do it. The same goes for robots or other machines, which are also referred to as agents. Advances in e.g. technology and science have made such agents more and more sophisticated and capable. This opens up a plethora of possibilities for solving problems or automating processes.
However, as agents and the problems they solve become more and more sophisticated, the software that controls these agents naturally also becomes more complex. Especially when considering systems of multiple cooperating agents. With rapidly increasing amounts of agents, observations and capabilities to take into account, the plans used to come to decisions become increasingly infeasible to create by hand. Thus automated methods are necessary to create such plans.
The approach this thesis uses is inspired by the ability of human intelligence to abstract away pedantic details when planning. We do not for example include which muscles we will utilize, when we make a plan for picking up groceries. Deciding to get groceries is on a completely different level than deciding how many centimeters we want to move a limb in a particular direction. Abstracting away such details greatly reduces the size of any potential plan. Which makes plans easier to construct, while the scope of the problem remains the same.
Thus, utilizing this notion of different levels of abstraction during planning, is the approach this thesis uses to improve planning for agents. This is done by extending the Macro Decentralized Partially Observable Markov Decision Process (MacDecPOMDP) framework to allow for an arbitrary number of levels of abstraction. ...
However, as agents and the problems they solve become more and more sophisticated, the software that controls these agents naturally also becomes more complex. Especially when considering systems of multiple cooperating agents. With rapidly increasing amounts of agents, observations and capabilities to take into account, the plans used to come to decisions become increasingly infeasible to create by hand. Thus automated methods are necessary to create such plans.
The approach this thesis uses is inspired by the ability of human intelligence to abstract away pedantic details when planning. We do not for example include which muscles we will utilize, when we make a plan for picking up groceries. Deciding to get groceries is on a completely different level than deciding how many centimeters we want to move a limb in a particular direction. Abstracting away such details greatly reduces the size of any potential plan. Which makes plans easier to construct, while the scope of the problem remains the same.
Thus, utilizing this notion of different levels of abstraction during planning, is the approach this thesis uses to improve planning for agents. This is done by extending the Macro Decentralized Partially Observable Markov Decision Process (MacDecPOMDP) framework to allow for an arbitrary number of levels of abstraction. ...
In order to do something useful, you should know what to do and how to do it. The same goes for robots or other machines, which are also referred to as agents. Advances in e.g. technology and science have made such agents more and more sophisticated and capable. This opens up a plethora of possibilities for solving problems or automating processes.
However, as agents and the problems they solve become more and more sophisticated, the software that controls these agents naturally also becomes more complex. Especially when considering systems of multiple cooperating agents. With rapidly increasing amounts of agents, observations and capabilities to take into account, the plans used to come to decisions become increasingly infeasible to create by hand. Thus automated methods are necessary to create such plans.
The approach this thesis uses is inspired by the ability of human intelligence to abstract away pedantic details when planning. We do not for example include which muscles we will utilize, when we make a plan for picking up groceries. Deciding to get groceries is on a completely different level than deciding how many centimeters we want to move a limb in a particular direction. Abstracting away such details greatly reduces the size of any potential plan. Which makes plans easier to construct, while the scope of the problem remains the same.
Thus, utilizing this notion of different levels of abstraction during planning, is the approach this thesis uses to improve planning for agents. This is done by extending the Macro Decentralized Partially Observable Markov Decision Process (MacDecPOMDP) framework to allow for an arbitrary number of levels of abstraction.
However, as agents and the problems they solve become more and more sophisticated, the software that controls these agents naturally also becomes more complex. Especially when considering systems of multiple cooperating agents. With rapidly increasing amounts of agents, observations and capabilities to take into account, the plans used to come to decisions become increasingly infeasible to create by hand. Thus automated methods are necessary to create such plans.
The approach this thesis uses is inspired by the ability of human intelligence to abstract away pedantic details when planning. We do not for example include which muscles we will utilize, when we make a plan for picking up groceries. Deciding to get groceries is on a completely different level than deciding how many centimeters we want to move a limb in a particular direction. Abstracting away such details greatly reduces the size of any potential plan. Which makes plans easier to construct, while the scope of the problem remains the same.
Thus, utilizing this notion of different levels of abstraction during planning, is the approach this thesis uses to improve planning for agents. This is done by extending the Macro Decentralized Partially Observable Markov Decision Process (MacDecPOMDP) framework to allow for an arbitrary number of levels of abstraction.
CryptoPIX
The Blockchain Based Daily Pixel Art Competition
Bachelor thesis
(2018)
-
Kees Fani, Pavel Hoogland, Manuel Borba da Silva Falcão Ferreira, Otto Visser, Rafael Bidarra
During the project the team aimed to make a decentralized web based game on the blockchain, that is fun to play and is indistinguishable from traditional centralized games. To accomplish this it was chosen to create the game on the EOS blockchain platform. The EOS blockchain platform features great improvements upon older more popular platforms such as Bitcoin and Ethereum. EOS brings improvements in transaction speed, scalability and control of user actions and data.
The creation of the game consisted of two parts. One was the web based application client and the other is the EOS smart contract. The smart contract was the place where all the game logic was programmed in, while the web application is used as an interface that makes it easy for players to communicate with the blockchain smart contract. ...
The creation of the game consisted of two parts. One was the web based application client and the other is the EOS smart contract. The smart contract was the place where all the game logic was programmed in, while the web application is used as an interface that makes it easy for players to communicate with the blockchain smart contract. ...
During the project the team aimed to make a decentralized web based game on the blockchain, that is fun to play and is indistinguishable from traditional centralized games. To accomplish this it was chosen to create the game on the EOS blockchain platform. The EOS blockchain platform features great improvements upon older more popular platforms such as Bitcoin and Ethereum. EOS brings improvements in transaction speed, scalability and control of user actions and data.
The creation of the game consisted of two parts. One was the web based application client and the other is the EOS smart contract. The smart contract was the place where all the game logic was programmed in, while the web application is used as an interface that makes it easy for players to communicate with the blockchain smart contract.
The creation of the game consisted of two parts. One was the web based application client and the other is the EOS smart contract. The smart contract was the place where all the game logic was programmed in, while the web application is used as an interface that makes it easy for players to communicate with the blockchain smart contract.