Agents-Artificial Intelligence with different types of agents
- 2. Agents and Environments Agent: An agent can be viewed as anything that perceives its environment through sensors and acts upon that environment through actuators. For example, human being perceives their surroundings through their sensory organs known as sensors and take actions using their hands, legs, etc., known as actuators. Agents interact with the environment through sensors and actuators. Terminologies: Percept: Agent’s perceptual inputs at any given instant. Percept sequence: Complete history of Everything the agent has ever perceived.
- 6. Behavior of an Agent Mathematically, an agent behavior can be described by an: • Agent Function: is a mathematical function that maps a sequence of perceptions into action. • Agent Program: The agent function for an artificial agent is implemented using program called agent program. Agent program is the concrete implementation running within some physical system. • The perception capability is usually called a sensor. • The actions can depend on the most recent perception or on the entire history (percept sequence). • The part of the agent taking an action is called an actuator.
- 10. Vacuum cleaner world problem Example There are two rooms and one vacuum cleaner. There is dirt in both the rooms. Vacuum cleaner present in any one room Goal – Clean both rooms Dirt Dirt Room 1 Room 2 Representation Vacuum cleaner is the agent Possible actions Move left Move Right Clean Dirt
- 11. Example Cont… 8 Possible states
- 12. Concept of Rationality Rational Agent: A rational agent is one that can take the right decision in every situation. An ideal rational agent is the one, which is capable of doing expected actions to maximize its performance measure, on the basis of − • Its percept sequence • Its built-in knowledge base Rationality of an agent depends on the following − • The performance measures, which determine the degree of success. • Agent’s Percept Sequence till now. • The agent’s prior knowledge about the environment. • The actions that the agent can carry out. • A rational agent always performs right action, where the right action means the action that causes the agent to be most successful in the given percept sequence.
- 13. Omniscient Agent: An omniscient agent is an agent which knows the actual outcome of its action in advance. However, such agents are impossible in the real world. Rational agents are different from Omniscient agents because a rational agent tries to get the best possible outcome with the current perception, which leads to imperfection. A chess AI can be a good example of a rational agent because, with the current action, it is not possible to foresee every possible outcome whereas a tic-tac-toe AI is omniscient as it always knows the outcome in advance.
- 14. Nature of Environment Environment is the place where the agent is going to work. To perform a task in an environment, the following are the important parameters need to be considered.. PEAS stands for Performance measures, Environment, Actuators, and Sensors. • Performance measures: These are the parameters used to measure the performance of the agent. How well the agent is carrying out a particular assigned task. • Environment: It is the task environment of the agent. The agent interacts with its environment. It takes perceptual input from the environment and acts on the environment using actuators. • Actuators: These are the means of performing calculated actions on the environment. • Sensors: These are the means of taking the input from the environment.
- 17. Sensors Actuators Human Agent Eyes, Ears, Nose…. Hands, Joints, Legs, Vocal Cord.. Robotic Agent Cameras, IR Sensors,.. Motors Software Agent Keystrokes, File contents,… Writing files, displaying on screen,..
- 20. Autonomous taxi Performance measure Safe, Fast, Legal, Comfortable Environment Roads, Traffic, Customers Actuators Steering, Accelerator, Braking, Horn, Sensors Camera, GPS, Odometer, Keyboard and Microphone…
- 22. Properties of task environments 1. Fully observable and Partially observable: An agent’s sensors give it access to complete state of the environment at each point in time, then we say that the task environment is fully observable; otherwise it is only partially observable. If the agent has no sensors at all then the environment is unobservable. Chess is fully observable: A player gets to see the whole board. Poker is partially observable: A player gets to see only his own cards, not the cards of anyone in the game.
- 26. 2. Single Agent / Multi Agents: An agent operating by itself in an environment is single agent. Multi agent is when other agents are present. For example: An agent solving a crossword puzzle by itself is clearly in a single-agent environment, whereas an agent playing chess is in a two agent environment. • A person left alone in a maze is an example of the single-agent system. • An environment involving more than one agent is a multi-agent environment. • The game of football is multi- agent as it involves 11 players in each team.
- 29. 3. Competitive vs Collaborative • An agent is said to be in a competitive environment when it competes against another agent to optimize the output. • The game of chess is competitive as the agents compete with each other to win the game which is the output. • An agent is said to be in a collaborative environment when multiple agents cooperate to produce the desired output. • When multiple self-driving cars are found on the roads, they cooperate with each other to avoid collisions and reach their destination which is the output desired.
- 30. 4. Deterministic vs Stochastic If the next state of the environment is completely determined by the current state and the actions of the agent, then the environment is deterministic; otherwise it is non-deterministic / stochastic. Deterministic Environment: Tic Tac Toe game. Non - Deterministic Environment: Self-driving vehicles.
- 33. 5. Episodic / Non-episodic ( Sequential ) In an Episodic task environment: Each of the agent’s actions is divided into atomic incidents or episodes (Each episode consists of the agent perceiving and then performing a single action ). There is no dependency between current and previous incidents. In each incident, an agent receives input from the environment and then performs the corresponding action. Example: Consider an example of Pick and Place robot, which is used to detect defective parts from the conveyor belts. Here, every time robot(agent) will make the decision on the current part i.e. there is no dependency between current and previous decisions. In a Sequential environment, the previous decisions can affect all future decisions. The next action of the agent depends on what action agent has taken previously and what action agent is supposed to take in the future. Example : Checkers- Where the previous move can affect all the following moves.
- 37. Pick and Place robot
- 38. 6. Dynamic vs Static An environment that keeps constantly changing itself when the agent is up with some action is said to be dynamic. An idle environment with no change in its state is called a static environment. If the environment does not change while an agent is acting, then it is static. Dynamic: Playing football game, other players make it dynamic. Every action there will be new reaction.
- 40. 7. Discrete vs Continuous If an environment consists of a finite number of actions that can be deliberated in the environment to obtain the output, it is said to be a discrete environment. • The game of chess is discrete as it has only a finite number of moves. The number of moves might vary with every game, but still, it’s finite. The environment in which the actions are performed cannot be numbered i.e. is not discrete, is said to be continuous. • Self-driving cars are an example of continuous environments as their actions are driving, parking, etc. which cannot be numbered.
- 43. 8. Known vs Unknown In a known environment, the output for all probable actions are given. In unknown environment, the agent will have to learn how it works in order to make good decisions.
- 45. Example
- 47. Structure of Agents The main goal of AI is to design an agent program that implements the agent function (the mapping from percepts to actions). Agent = physical sensors and actuators + program Architecture Agent = architecture + program
- 48. Agent programs The agent program takes current percept as input from the sensors and return an action to the actuators. The agent program takes the current percept as input, and the agent function, which takes the entire percept history. ; if the agent’s actions need to depend on the entire percept sequence, the agent will have to remember the percepts. Types of Agents Agents can be grouped into five classes based on their degree of perceived intelligence and capability : • Simple Reflex Agents • Model-Based Reflex Agents • Goal-Based Agents • Utility-Based Agents • Learning Agent
- 49. Simple reflex agents • The Simple reflex agents are the simplest agents. These agents take decisions on the basis of the current percepts and ignore the rest of the percept history. • These agents only succeed in the fully observable environment. If it is partially observable, in that case the agent function enters into infinite loops that can be escaped only on randomization of its actions. • The Simple reflex agent does not consider any part of percepts history during their decision and action process. • The Simple reflex agent works on Condition-action rule, which means it maps the current state to action. If the condition is true, then the action is taken, else not.
- 50. Simple reflex agents Function Simple-Reflex-Agent(percept) static: rules, /* condition-action rules */ state <- Intercept_input(percept) rule <- Rule_match(state, rules) action <- Rule_Action(rule) return(action) The vacuum agent is a simple reflex agent because the decision is based only on the current location, and whether the place contains dirt.
- 51. Model-based reflex agents A model-based agent can handle partially observable environments. It consists of two important factors, which are Model and Internal State. Model provides knowledge which helps in understanding of the occurrence of different things in the environment such that the current situation can be studied and a condition can be created then appropriate actions are performed by the agent. Internal State uses the perceptual history to represent a current percept. The agent keeps a track of this internal state and is adjusted by each of the percepts. The internal state is stored by the agent to describe the unseen world. The state of the agent can be updated by gaining information about how the environment evolves and how the agent's action affects the environment.
- 52. Model-based reflex agents Function Reflex-Agent-With-State(percept) static: state, /* description of the current world state */ rules // set of condition-action rules // state <- Update_State(state, percept) rule <- Rule_Match(state, rules) action <- Rule_Action(rule) state <- Update_State(state, action) return(action)
- 55. Goal-based agents These kinds of agents take decisions based on how far they are currently from their goal. Their every action is intended to reduce its distance from the goal. This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state. The knowledge that supports its decisions is represented explicitly and can be modified, which makes these agents more flexible. They usually require search and planning. It is an improvement over model based agent where information about the goal is also included. This is because it is not always sufficient to know just about the current state, knowledge of the goal is a more beneficial approach.
- 57. Function Goal-Based-Agent(percept) static: state, /* description of the current world state */ rules /* set of condition-action rules */ goal /* set of specific success states */ state <- Update_State(state, percept) rule <- Rule_Match(state, rules) action <- Rule_Action(rule) state <- Update_State(state, action) if (state in goal) then return (action) else percept <- Obtain_Percept(state, goal) return(Goal-Based-Agent(percept))
- 59. Utility-based agents • Utility agent uses building blocks which will help in taking the best actions and decisions when multiple alternatives are present. • It is an improvement over goal based agent as it not only involves the goal but also the way the goal can be achieved such that the goal can be achieved in a quicker, safer, cheaper way. • When there are multiple possible alternatives, then to decide which one is best, utility-based agents are used. They choose actions based on a preference (utility) for each state. Utility describes how “happy” the agent is. Utility: A function which maps a state (successful) into a real number (describes associated degree of success). • Because of the uncertainty in the world, a utility agent chooses the action that maximizes the expected utility. A utility function maps a state onto a real number which describes the associated degree of happiness.
- 62. Function Goal-Based-Agent(percept) static: state, /* description of the current world state */ rules /* set of condition-action rules */ goal /* set of specific success states */ state <- Update_State(state, percept) rule <- Rule_Match(state, rules) action <- Rule_Action(rule) state <- Update_State(state, action) score <- Obtain_Score(state) if (state in goal) and Best_Score(score) then return(action) else percept <- Obtain_Percept(state, goal) return(Goal-Based-Agent(percept))
- 63. Learning Agent Learning agent, as the name suggests, has the capability to learn from past experiences and takes actions or decisions based on learning capabilities. It starts to act with basic knowledge and then is able to act and adapt automatically through learning. A learning agent has mainly four conceptual components, which are: • Learning element: It is responsible for making improvements by learning from the environment • Critic: The learning element takes feedback from critics which describes how well the agent is doing with respect to a fixed performance standard. • Performance element: It is responsible for selecting external action • Problem Generator: This component is responsible for suggesting actions that will lead to new and informative experiences.
- 64. Learning Agent
- 65. Thank You
Editor's Notes
- #3: An object is perceived by humans through sensor organs
- #4: Its full automated car its receives the sensors through the environment
- #5: Objects are appearing and disappearing-we will have one start point –to form circle s called percept sequence
- #7: It will perceives the temperature of the room (withhelp of actuators its adjust to environment condition
- #8: Agent function-what input your getting from the environment what action I should be taken
- #33: The episodic environment is also called the non-sequential environment. In an episodic environment, an agent's current action will not affect a future action, whereas in a non-episodic environment, an agent's current action will affect a future action and is also called the sequential environment.
- #44: In solitare card games I know the rules but am not able to see the cards that have not turned over. In unknwn –video games the screen may show the entire game state but what button will do until I try them.
- #50: The actions are taken depending upon the condition. If the condition is true, the relevant action is taken. If it is false, the other action is taken. The agent takes input from the environment through sensors, and delivers the output to the environment through actuators.
- #52: What differentiates a model-based reflex agent from a simple reflex agent? A model-based agent relies only on current understanding. A simple reflex agent is more sophisticated. A model-based agent can incorporate percept history. A simple reflex agent only looks at percept history.
- #55: Alibaba(g+) robot agent in Amazon delivers to customers based on goal based agent
- #62: What is the primary function of the utility-based agent? Making the best choice. Reaching its intended goal. Improving its thought processes. Delivering actuator data.