IAI | HSLU | Jana Köhler

To handle situations where the environment is not fully observable and avoid infinite loops, Simple Reflex Agents can introduce randomization to break out of stuck states. This randomization allows for exploratory actions.

A Model-based Reflex Agent keeps an internal world model that depends on the agent's percept sequence, allowing it to consider past percepts and anticipate the effects of actions, whereas a Simple Reflex Agent responds based only on the current percept.

The internal world model of a Model-based Reflex Agent can answer questions about the effects of agent actions and how the environment evolves independently of the agent. This information helps the agent make more informed decisions.

Uncertainty in the internal world model is unavoidable due to the agent's limited sensing capabilities and the challenges of creating accurate models. The model represents the agent's "best guess" of the environment state, its evolution, and the effects of actions, given the available information.

A Model-based Reflex Agent addresses these challenges by maintaining an internal world model that allows it to make informed decisions based on its "best guess" of the environment state and action effects, even when there is uncertainty due to limitations.

If several actions are possible in a state, this agent can evaluate their utility and make a deliberate choice

This agent can acquire new skills and reflect on its own performance to improve over time

Learning Agents can become more competent over time through learning and adaptability.

Yes, Learning Agents can operate in initially unknown environments and start with an empty knowledge base.

The components include:

1. Performance element (current learned model)
2. Learning element (improves performance through learning)
3. Critic (evaluates behavior and provides feedback)
4. Problem generator (suggests actions for informative experiences).

• Builds a model of the world and uses an explicit representation of goals
• Considers effects of actions on the world model before selecting an action to achieve a goal state - to choose among competing actions/goals utility function is needed

The goal-based agent selects actions based on their effects towards a goal in the future and can therefore also select actions that temporally lead to a state with worse utility

Agent architectures that we distinguish include Simple Reflex Agent, Model-based Reflex Agent, Goal-based Agent, Utility-based Agent, and Learning Agent.

The model-based reflex agent is more intelligent because it maintains an internal world model, allowing it to consider past percepts and anticipate action effects, which enables more informed and flexible decision-making.

The key difference is in their decision criteria. A utility-based agent maximizes expected utility, considering the desirability of outcomes, while a goal-based agent focuses on achieving specific goals or objectives.

The critic evaluates the behavior of the learning agent based on its performance and provides feedback to the learning element, assisting in the agent's learning and improvement process.

A problem generator suggests actions that lead to informative experiences, helping the learning agent explore and gather valuable data to improve its knowledge and decision-making.

To achieve human-level AI, we need sophisticated agent architectures that are capable of learning, adapting, and making intelligent decisions. A combination of learning agents and other advanced architectures may be necessary.