Introduction to AI Agent (Part II)

A. Agent architectures

We will next discuss various agent architectures.

·        Table based agent

In table based agent the action is looked up from a table based on information about the agent’s percepts. A table is simple way to specify a mapping from percepts to actions. The mapping is implicitly defined by a program. The mapping may be implemented by a rule based system, by a neural network or by a procedure.

There are several disadvantages to a table based system. The tables may become very large. Learning a table may take a very long time, especially if the table is large. Such systems usually have little autonomy, as all actions are pre-determined.

·        Percept based agent or reflex agent

In percept based agents,

1. Information comes from sensors - percepts

2. Changes the agents current state of the world

3. Triggers actions through the effectors

Such agents are called reactive agents or stimulus-response agents. Reactive agents have no notion of history. The current state is as the sensors see it right now. The action is based on the current percepts only.

The following are some of the characteristics of percept-based agents.

            • Efficient

            • No internal representation for reasoning, inference.

            • No strategic planning, learning.

            • Percept-based agents are not good for multiple, opposing, goals.

·        Subsumption Architecture

We will now briefly describe the subsumption architecture (Rodney Brooks, 1986). This architecture is based on reactive systems. Brooks notes that in lower animals there is no deliberation and the actions are based on sensory inputs. But even lower animals are capable of many complex tasks. His argument is to follow the evolutionary path and build simple agents for complex worlds.

The main features of Brooks’ architecture are.

            • There is no explicit knowledge representation

            • Behaviour is distributed, not centralized

            • Response to stimuli is reflexive

            • The design is bottom up, and complex behaviours are fashioned from the combination of simpler underlying ones.

            • Individual agents are simple

The Subsumption Architecture built in layers. There are different layers of behaviour. The higher layers can override lower layers. Each activity is modeled by a finite state machine. The subsumption architecture can be illustrated by Brooks’ Mobile Robot example.

Subsumption Architecture

The system is built in three layers.

            1. Layer 0: Avoid Obstacles

            2. Layer1: Wander behavior

            3. Layer 2: Exploration behavior

·        State-based Agent or model-based reflex agent

State based agents differ from percept based agents in that such agents maintain some sort of state based on the percept sequence received so far. The state is updated regularly based on what the agent senses, and the agent’s actions. Keeping track of the state requires that the agent has knowledge about how the world evolves, and how the agent’s actions affect the world.

Thus a state based agent works as follows:

            • information comes from sensors - percepts

            • based on this, the agent changes the current state of the world

            • based on state of the world and knowledge (memory), it triggers actions through the effectors

·        Goal-based Agent

The goal based agent has some goal which forms a basis of its actions.

Such agents work as follows:

            • information comes from sensors - percepts

            • changes the agents current state of the world

            • based on state of the world and knowledge (memory) and goals/intentions, it chooses actions and does them through the effectors.

·        Utility-based Agent

Utility based agents provide a more general agent framework. In case that the agent has multiple goals, this framework can accommodate different preferences for the different goals.

Such systems are characterized by a utility function that maps a state or a sequence of states to a real valued utility. The agent acts so as to maximize expected utility

·        Learning Agent

Learning allows an agent to operate in initially unknown environments. The learning element modifies the performance element. Learning is required for true autonomy

B. Conclusion

In conclusion AI is a truly fascinating field. It deals with exciting but hard problems. A goal of AI is to build intelligent agents that act so as to optimize performance.

            • An agent perceives and acts in an environment, has an architecture, and is implemented by an agent program.

            • An ideal agent always chooses the action which maximizes its expected performance, given its percept sequence so far.

            • An autonomous agent uses its own experience rather than built-in knowledge of the environment by the designer.

            • An agent program maps from percept to action and updates its internal state.

            • Reflex agents respond immediately to percepts.

            • Goal-based agents act in order to achieve their goal(s).

            • Utility-based agents maximize their own utility function.

            • Representing knowledge is important for successful agent design.

• The most challenging environments are partially observable, stochastic, sequential, dynamic, and continuous, and contain multiple intelligent agents.

That is the end of the discussion about AI Agents. I am always free for any query and suggestion about the topic.