Download “Intelligent” Agents

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Ecological interface design wikipedia , lookup

Existential risk from artificial general intelligence wikipedia , lookup

Philosophy of artificial intelligence wikipedia , lookup

Enactivism wikipedia , lookup

History of artificial intelligence wikipedia , lookup

Agent (The Matrix) wikipedia , lookup

Ethics of artificial intelligence wikipedia , lookup

Cognitive model wikipedia , lookup

Embodied cognitive science wikipedia , lookup

Transcript
Kybernetik
“Intelligent” Agents- Decision Making
Mohamed Oubbati
Institut für Neuroinformatik
Tel.: (+49) 731 / 50 24153
[email protected]
03. 07. 2012
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
“Intelligent” Agents
Environment
Agent
“Intelligent” Agents continuously perform 4 functions:
1.
2.
3.
4.
Perception (sensory data + interpretation).
Reasoning.
Decision making.
Action selection to affect the environment in order to meet their
design objective.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
“Intelligent” Agents
Environment
Agent
“Intelligent” Agents continuously perform 4 functions:
1. Perception (sensory data + interpretation).
2. Reasoning.
3. Decision making.
4. Action selection to affect the environment in order to meet their
design objective.
How to make decisions?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
• Reactive
• Pro-active
• Social
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
• Reactive
• Pro-active
• Social
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
Reactive
Environment
Agent
Perception
(World state)
Conditions rules
stimulus → response
(e.g. if-then-else)
Action Execution
this is a simple reflex agent...
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
Model-based Reactive
Agent
Environment
Forward Model
(how the world evolves)
Past
Experiences
Perception
(World state)
Internal State
Conditions
rules
Action Execution
this agent is reactive but uses its internal state...
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
Pro-active
An agent is generally asked to do things, i.e. his
existence should have a sense (for us).
Pro-activeness means taking the initiative in
order to achieve goals; not simply reacting to
preceived events.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
Pro-active
Agent
Environment
Forward Model
(how the world evolves)
Past
Experiences
Perception
(World state)
Internal State
Goal
What action should
be selected?
Action Execution
this agent has a goal directed behavior...
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to design an agent?
Balancing Reactive and Pro-active
It is desirable that agents systematically work towards
long-term goals, but also react appropriately to
changing conditions .
This remains an open research problem
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
back to the important question:
how to make decisions?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
1. Let’s consider an agent in a complex, dynamic,
and sometimes novel environment.
2. This agent has to follow a long-term goal.
How to proceed?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
1. Let’s consider an agent in a complex, dynamic,
and sometimes novel environment.
2. This agent has to follow a long-term goal.
How to proceed?
Maybe research in Artificial Intelligence (AI) can help.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
NO
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
NO
- by training the agent to learn the consequences of every possible
action in every situation?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
NO
- by training the agent to learn the consequences of every possible
action in every situation?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
NO
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
NO
- by training the agent to learn the consequences of every possible
action in every situation?
NO
What would the AI guys say?
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
- by pre-programming the agent for every possible situation?
NO
- by training the agent to learn the consequences of every possible
action in every situation?
NO
What would the AI guys say?
1. If situations have been seen before, the agent has simply to
remember what has tried in the past.
2. If situations are slightly different, the agent would be able
generalise from what it has learned.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
What about completely new situations?
actual AI: ?!
That might explain, for example, why until
this moment their are no cars that can
navigate autonomously (without driver) in
urban streets.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
How to make decisions?
How to proceed?
What about completely new situations?
actual AI: ?!
That might explain, for example, why until
this moment their are no cars that can
navigate autonomously (without driver) in
urban streets.
• It is time to thing about a new AI that considers intelligence as
a whole, and not only for pre-specified applications…
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
New AI
An agent should be intelligent, in an abstract sense,
without being specialized in pre-defined tasks.
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
New AI
An agent should be intelligent, in an abstract sense,
without being specialized in pre-defined tasks.
… but how to program an agent without even
knowing the task?
This is the challenge of the new (since 2001) field of
research:
Artificial General Intelligence (AGI)
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12
Danke für die Zusammenarbeit
und viel Erfolg bei der Klausur
Dr. Oubbati, Kybernetik (Neuroinformatik, Uni-Ulm)
“Intelligent” Agents- Decision Making
SoSe12