310 likes | 439 Views
Agents with Personality: Negotiating Agents and Marital Stability. Vicki H. Allan Sponsored by CURI (Community/University Research Initiative). An Agent in its Environment. AGENT. action output. Sensor Input. ENVIRONMENT. “Agent enjoys the following properties:
E N D
Agents with Personality:Negotiating Agents and Marital Stability Vicki H. Allan Sponsored by CURI (Community/University Research Initiative)
An Agent in its Environment AGENT action output Sensor Input ENVIRONMENT
“Agent enjoys the following properties: • autonomy - agents operate without the direct intervention of humans or others, and have some kind of control over their actions and internal state; • social ability - agents interact with other agents (and possibly humans) via some kind of agent-communication language; • reactivity: agents perceive their environment and respond in a timely fashion to changes that occur in it; • pro-activeness: agents do not simply act in response to their environment, they are able to exhibit goal-directed behaviour by taking initiative.” (Wooldridge and Jennings, 1995)
Agents • Need for computer systems to act in our best interests • “The issues addressed in multiagent systems have profound implications for our understanding of ourselves.” Wooldridge • Example – how do you make a decision about buying a car
Agent Environments • not have complete control (influence only) (heating in Old Main) • deterministic vs non-deterministic effect • accessible (get complete state info) vs inaccessible environment (stock market) • episodic vs non-episodic (history sensitive) (grades in class)
Emotional agents • A computable science of emotions • Virtual actors • Listen through speech recognition software to people • Respond, in real time, with morphing faces, music, text, and speech • manifest temperament control of emotions
BDI (Belief-Desire-Intention) architectures • High-level specifications: practical component of an architecture for a resource-bounded agent. • It performs means-end analysis, weighing of competing alternatives for achieving a specific goal (desire). • Beliefs = information the agent has about the world • Desires = state of affairs that the agent would wish to bring about • Intentions = desires the agent has committed to achieve –lead to an action, options consistent • intentions play a critical role in practical reasoning - limits options, simpler, must be updated, not persist too long 7
Idea: What if we programmed an agent to act like a person in a social situation? Could a person learn something valuable by seeing his behavior? Could a person benefit by replaying the situation using a new set of behaviours? 8
Program Agents with Personality and Emotion • Bob and Alice are considering marriage. • Evaluate their personalities • Agent Bob and Agent Alice • Give Agents a problem and view how they negotiate.
Goal: Create better communication “My wife and I had words, but I never got to use mine.” -Fibber McGee
Goal: Create more realistic expectations • Young girl: Is it true, Mom, I heard that in some parts of Africa a woman doesn’t know her husband until she marries him? • Mom: That happens in every country, dear.
Happiness is a function of expectation • relative to what you expected
Goal: help an individual to find a compatible mate • “It was a mixed marriage. I’m human, he was a Klingon.” -Carol Leifer.
Marital Research • How a couple differs is not so important (as there will always be differences). • What is important is how they deal with those differences.
Goals of this research • Model human interaction reliably • Help individuals make appropriate marital decisions • Help individual to change his/her destructive habits
Other possible uses • Evaluate group dynamics – before space shuttle, for example. • Train individual to deal with emergencies by simulating various emergencies. Believability is key. • Teacher training – classroom management.
How differ from other agent interactions? • In interpersonal conflicts, the winner may actually lose. (agree to watch the movie, but be poor company) • The synergy of two people’s ideas could be better than either alone. • Competing with people usually deteriorates the quality of the relationship in other areas. • Finding a common solution may enable a couple to grow together rather than apart. (e.g. finding a common activity)
Why is research valuable? • Of first marriages, roughly 40-50% will end in divorce. • Marital problems/divorce • lower work productivity • mental problems • physical problems • anti-social behavior • poverty • low self-esteem
Several studies suggest • Researchers can predict which marriages will end in failure from information gathered before the couple marries. • Tell people they are at substantially greater risk for divorce • Told couples argue most about children and money, but some believe how they argue is most important.
Interaction Patterns • speaker/listener (take roles) • criticism • defensiveness • contempt • stonewalling (listener withdrawal emotionally and perhaps physically) • kitchen sink (prior complaints brought up)
Modeling Emotions • Emotions are important in giving Disney characters the illusion of life. • Believability vs realism: may be better to use simplified, exaggerated characters.
Joy Fear/anxiety Like/dislike anger shame/remorse startle interest sadness disgust/contempt shyness love Which emotions to model? Other systems have as many as 25 emotions
How to Combine Emotions • Winner take all – ignore all but the highest intensity emotion • Additive – but may be confusing to model joy and sadness simulataneously • Logarithmic: log(2emotion1 + 2emotion2) • Focus – kicking example
How express emotions? • Facial expressions • What the character does • How he does it • What words are chosen • emotions are integral, cannot be removed – but reaction to emotion is highly dependent on personality and other features
How created • Reilly: demons exist which trigger emotion structure in response to a failed goal. Emotion is created, but must be queried by action component. • Also important is surprise, importance of goal, difference in emotion felt with success or failure of same goal. (e.g., goal: to have companion)
Goals • Intensity • Chance of succeeding • Emotions generated when fail • Emotions generated when chance of succeeding increases/decreases.
Behavior Features: map emotions to actions • type (cheerful, friendly, aggressive, defensive) • intensity • direction – who is behavior directed towards • cause – what is the cause of the behavior
What kind of transformations? • Decay – all at same rate? • Combine • Filter Idea: create an algebra of emotions through matrix manipulation
What effects emotions? • Personality – each personality type will express emotions in its own way. • relationships: affect what emotions are felt and how strongly • memory: previous experiences (Were you angry when the first telemarketer called?)
Concerns • Cardboard personalities? • Different personalities/scenarios? • If we allow the user to control an agent, can the personality still be seen? (Alphawolves) • How do we test it? (subjective tests?)
After a quarrel, a husband said to his wife, “You know, I was a fool when I married you.” The wife replied, “Yes dear, but I was in love and didn’t notice.” • I married Mr Right. I just didn’t know his first name was Always.