A Cognitive Framework for Delegation to an Assistive User Agent Karen Myers and Neil Yorke-Smith Artificial Intelligence Center, SRI International.

Slides:



Advertisements
Similar presentations
Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Advertisements

Pat Langley Computational Learning Laboratory Center for the Study of Language and Information Stanford University, Stanford, California USA
Pat Langley Institute for the Study of Learning and Expertise Palo Alto, California A Cognitive Architecture for Complex Learning.
Twelve Cs for Team Building
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Workpackage 2: Norms
Towel: Towards an Intelligent ToDo List Ken Conley Jim Carpenter SRI International AAAI Spring Symposium 2007.
Making the Grade Grading Practices for Students with Disabilities By Cathy Sartain Industries
Mixed-Initiative Planning Yolanda Gil USC CS 541 Fall 2003.
Foundations of Team Leadership
Scheduling with Uncertain Resources Reflective Agent with Distributed Adaptive Reasoning RADAR.
Introduction to CSE 591: Autonomous agents - theory and practice. Chitta Baral Professor Department of Computer Sc. & Engg. Arizona State University.
Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.
4-1 Chapter 4: PRACTICAL REASONING An Introduction to MultiAgent Systems
IACT901 - Module 1 Planning Theory - Scope & Integration ABRS Hong Kong 2004 Penney McFarlane University of Wollongong.
BDI Agents Martin Beer, School of Computing & Management Sciences,
Presented by TS Hamilton. Five Core Competencies We link our courses to CalSTRS core competencies.
Planning. SDLC Planning Analysis Design Implementation.
Opportunities & Implications for Turkish Organisations & Projects
CSC271 Database Systems Lecture # 20.
So What Can I Expect When I Serve on an NEASC/CPSS Visiting Team? A Primer for New Team Members.
Develop your Leadership skills
Thinking Actively in a Social Context T A S C.
Problem Solving.  Critical Thinking enables a person to solve problems and make decisions. Therefore - Problem solving and decision making are practical.
1 CREATING A LEARNING ORGANIZATION AND AN ETHICAL ORGANIZATION STRATEGIC MANAGEMENT BUAD 4980.
30 May 2001Autonomous Agents1 The BOID architecture ( Conflicts Between Beliefs, Obligations, Intentions and Desires ) Jan Broersen Mehdi Dastani Joris.
Collectively Cognitive Agents in Cooperative Teams Jacek Brzeziński, Piotr Dunin-Kęplicz Institute of Computer Science, Polish Academy of Sciences Barbara.
Presentation Contents What do we mean by Personal Development? What is the process for doing this activity? How does PD relate to PAR? What are the steps.
SLB /04/07 Thinking and Communicating “The Spiritual Life is Thinking!” (R.B. Thieme, Jr.)
L 9 : Collaborations Why? Terminology Coherence Coordination Reference s :
THE OSCAR PROJECT Rational Cognition in OSCAR John L. Pollock Department of Philosophy University of Arizona Tucson, Arizona 85721
December 14, 2011/Office of the NIH CIO Operational Analysis – What Does It Mean To The Project Manager? NIH Project Management Community of Excellence.
Belief Desire Intention Agents Presented by Justin Blount From Reasoning about Rational Agents By Michael Wooldridge.
Ahmad Al-Ghoul. Learning Objectives Explain what a project is,, list various attributes of projects. Describe project management, discuss Who uses Project.
EEL 5937 Models of agents based on intentional logic EEL 5937 Multi Agent Systems.
Automated Assistant for Crisis Management Reflective Agent with Distributed Adaptive Reasoning RADAR.
1 USC INFORMATION SCIENCES INSTITUTE CALO, 8/8/03 Acquiring advice (that may use complex expressions) and action specifications Acquiring planning advice,
April 22, 2002VMASC Board Meeting Issues in Enhancing Simulation Model Reuse C. Michael Overstreet Richard E. Nance Osman Balci.
Teambuilding For Supervisors. © Business & Legal Reports, Inc Session Objectives You will be able to: Recognize the value of team efforts Identify.
Jan. 29, 2002Grand Challenges in Simulation Issues in Enhancing Model Reuse C. Michael Overstreet Richard E. Nance Osman Balci.
Problem Solving / Decision MakingChapter Problem Solving / Decision Making Kepner-Tregoe The New Rational Manager Chapter 1.
National Math Panel Final report 2008 presented by Stanislaus County Office of Education November 2008.
Project Management Planning Minder Chen, Ph.D. CSU Channel Islands
Geoinformatics 2006 University of Texas at El Paso Evaluating BDI Agents to Integrate Resources Over Cyberinfrastructure Leonardo Salayandía The University.
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
Management Practices Lecture Recap Conflict Management Strategies for Dealing with Conflict Conflict Resolution Skills 2.
Module 5 Session 5.2 Visual 1 Module 5 Refining Objectives, Scope, and Other Project Parameters Session 5.2 Reviewing the PAR and refining key project.
University of Kurdistan Artificial Intelligence Methods (AIM) Lecturer: Kaveh Mollazade, Ph.D. Department of Biosystems Engineering, Faculty of Agriculture,
Teaching Games for Understanding (TGfU) As a Curriculum Model
AAAI Fall Symposium on Mixed-Initiative Problem-Solving Assistants 1 Mixed-Initiative Dialogue Systems for Collaborative Problem-Solving George Ferguson.
Organization Development and Change © PAPERHINT.COM.
Process Asad Ur Rehman Chief Technology Officer Feditec Enterprise.
Elementary School Administration and Management GADS 671 Section 55 and 56.
Business Ethics: Ethics can be defined as standards or principles of conduct that govern the behavior of an individual or a group of individuals. Ethics.
Leadership & Teamwork. QUALITIES OF A GOOD TEAM Shared Vision Roles and Responsibilities well defined Good Communication Trust, Confidentiality, and Respect.
RULES Patty Nordstrom Hien Nguyen. "Cognitive Skills are Realized by Production Rules"
Automated Assistant for Crisis Management (Reflective Agent with Distributed Adaptive Reasoning) RADAR.
Agent-Based Dialogue Management Discourse & Dialogue CMSC November 10, 2006.
Team Building and Motivation ITC/ILO Workshop on Decent Work for Transport Workers Oct Prepared by Victoria Munsey.
The Four Enablers of Strategy 24 February The Four Enablers of Strategy Systems Structure Capability CultureStrategy.
1 KM Track Overview & Gaining Value from Knowledge -- Knowledge Management (KM) and the Contracting Professional Breakout Session # 119 Name: Gaining.
Performance Management Q&A Sessions November 10, 2010.
So what can I expect when I serve on a NEASC/CPSS Visiting Team?
Empower Managers to Take Ownership of Employee Engagement
Activity Flow Design - or - Organizing the users’ Work
Organization Development
Issues in Enhancing Model Reuse
Developing an Intelligent User Assistant: Five Observations from CALO
Presentation transcript:

A Cognitive Framework for Delegation to an Assistive User Agent Karen Myers and Neil Yorke-Smith Artificial Intelligence Center, SRI International

Overview CALO: a learning cognitive assistant User delegation of tasks to CALO Delegative BDI agent framework Goal adoption and commitments Summary and research issues

CALO: Cognitive Assistant that Learns and Organizes CALO supports a high-level knowledge worker Understands the “office world”, your projects and schedule Performs delegated tasks on your behalf Works with you to complete tasks Stays with you (and learns) over long periods of time Learns to anticipate and fulfill your needs Learns your preferred way of working Track execution of project tasks Help manage time and commitments Perform tasks in collaboration with the user

CALO Year 2

Overview CALO: a learning cognitive assistant User delegation of tasks to CALO Delegative BDI agent framework Goal adoption and commitments Summary and research issues

Delegation May Lead to Conflicts Focus on delegation of tasks from user to CALO Not on tasks to be performed in collaboration One aspect of CALO’s role as intelligent assistant CALO cannot act if conflicts over actions Conflicts in tasks “purchase this computer on my behalf” “register me for the Fall Symposium” Conflicts in guidance “always ask for permissions by ” “never use for sensitive purchases”

Conflicts in User’s Desires “I wish to be thin” “I wish to eat chocolate” But Richard Waldinger’s scotch mocha brownies are full of calories  conflict between incompatible desires User’s desires conflict with each other Humans seem to have no problem with such conflicts CALO must recognize and respond appropriately

Other Types of Conflicts Current and new commitments Currently CALO is undertaking tasks to: Purchase an item of computer equipment Register user for a conference Now user tasks CALO to register for a second conference Set of new goals is logically consistent and coherent But infeasible because insufficient discretionary funds Commitments and advice User tasks CALO to schedule visitor’s seminar in best conference room Existing advice: “Never change a booking in the auditorium without consulting me” New goal and existing advice are inconsistent

The BDI Framework CALO’s ability to act is based on BDI framework Beliefs = informational attitudes about the world Desires = motivational attitudes on what to do Intentions = deliberative commitments to act Realized in the SPARK agent system Hierarchical, procedural reasoning framework BDI components in SPARK represented as: Facts (beliefs) Intentions (goals/intentions) Desires are not represented Procedures are plans to achieve intentions

Desires vs. Goals Both are motivational attitudes Desires may be neither coherent (with beliefs) nor consistent (with each other) Goals must be both Desires are ‘wishes’; goals are ‘wants’ “I wish to be thin and I wish to eat chocolate” “I want to have another of Richard’s brownies” Desires lead to goals CALO’s primary desire: satisfy its user Secondary desires→goals to do what user asks

‘BDI’ Agents are Really ‘BGI’ Decision theory emphasizes B and D AI agent theory emphasizes B and I In most BDI literature, ‘Desires’ and ‘Goals’ are confounded In practice, focus is on: goal and then intention selection option generation, and plan execution and scheduling Focus has been much less on: deliberating over desires goal generation advisability vital for CALO

The Problem with BGI When Desires and Goals are unified into a single motivational attitude: Can’t support conflicting D/G (and D/B) Hard to express goal generation Hard to diagnose and resolve conflicts Between D/G and I, and between G, I, and plans Hard to handle conflicts in advice How can CALO make sense of the user’s taskings in order to act upon them? How can CALO recognize and respond to (potential) conflicts?

Overview CALO: a learning cognitive assistant User delegation of tasks to CALO Delegative BDI agent framework Goal adoption and commitments Summary and research issues

Cognitive Models for Delegation agent GAGA Belief B user (do assigned tasks) user B agent Desire Goal D user D agent G user G C agent alignment delegation refinement decision making goal adoption Candidate Goals Adopted Goals satisfy all tasks

Delegative BDI Agent Architecture user failure conflicts revision advice AEAE AGAG agent GCGC GAGA I execute B sub-goaling B D G Candidate GoalsAdopted GoalsIntentions Goal AdviceExecution Advice

Overview CALO: a learning cognitive assistant User delegation of tasks to CALO Delegative BDI agent framework Goal adoption and commitments Summary and research issues

Requirements on Goal Adoption Self-consistency: G A must be mutually consistent Coherence: G A must be mutually consistent relative to the current beliefs B Feasibility: G A must be mutually satisfiable relative to current intentions I and available plans Includes resource feasibility Reasonableness: G A should be mutually ‘reasonable’ with respect to current B and I Common sense check: did you really mean to purchase a second laptop computer today?

Responding to Conflicting Desires Goal adoption process should admit: Adopting, suspending, or rejecting candidate goals Modifying adopted goals and/or intentions Modifying beliefs (by acting to change world state) Example: User desires to attend a conference in Europe but lacks sufficient discretionary funds shorten a previously scheduled trip cancel the planned purchase of a new laptop or apply for a travel grant from the department

Combined Commitment Deliberation Goal adoption Adopted Goals  Candidate Goals (  Desires) Intention reconsideration Extended agent life-cycle Non-adopted Candidate Goals Execution problems with Adopted Goals Propose combined commitment deliberation mechanism Based on agent’s deliberation over its mental states Bounded rationality: as far as the agent believes and can compute

BDI Control Cycle identify changes to mental state decide on response perform actions world state changes commitment deliberation

Mental State Transitions Current mental state S = (B,G C,G A,I) Omit D since suppose single “satisfy user” desire Outcome of deliberation is new state S' Possible new transitions: Expansionadopt additional goal No modification to existing goals or intentions Revocationdrop adopted goal + intention To enable a different goal in the future Proactivecreate new candidate goal and adopt it To enable a current candidate goal in the future Plus standard BGI transitions E.g. drop an intention due to plan failure observe decide act commitment deliberation

Goal and Intention Attributes Goals: User-specified value/utility Can be time-varying User-specified priority User-specified deadline Estimate cost to achieve Level of commitment so far For adopted goals Intentions: Implied value/utility Cost of change Deliberative effort Loss of utility Delay Level of commitment Level of effort so far E.g. estimated % complete Estimated cost to complete Estimated prob. success

Making the Best Decision S→S' transition as multi-criteria optimization Maximize (minimize) some combination of criteria over S Can be simple or complex Bounded rationality Simple default strategy, customizable by user Advice acts as constraints  constrained (soft) multi-criteria optimization problem “Don’t drop any intention > 70% complete” Assistive agent can consult user if no clear best S' “Should I give up on purchasing a laptop, in order to satisfy your decision to travel to both conferences?” Learn and refine model of user’s preferences

Example Candidate goals: c 1 : “Purchase a laptop” c 2 : “Attend AAAI” Adopted goals and intentions: g 1 with intention i 1 : “Purchase a high-end laptop using general funds” g 2 with intention i 2 : “Attend AAAI and its workshops, staying in conference hotel” New candidate goal from user: c 3 : “Attend AAMAS” (high priority) Mental state S = (B, {c 1,c 2,c 3 }, {g 1,g 2 }, {i 1,i 2 })

Example (cont.) CALO finds cannot adopt c 3 {g 1,g 2,g 3 } resource contention – insufficient general funds Options include: 1. Do not adopt c 3 (don’t attend AAMAS) 2. Drop c 1 or c 2 (laptop purchase or AAAI attendance) 3. Modify g 2 to attend only the main AAAI conference But changing i 2 incurs a financial penalty 4. Adopt a new candidate goal c 4 to apply for a departmental travel grant Advice prohibits option 2

Example (cont.) CALO builds optimization problem and solves it Problem constructed and solution method employed both depend on agent’s nature E.g. ignore % of intention completed No more than 10ms to solve Finds best is tie between options 3 and 4 Agent’s strategy (based on user guidance) is to consult user over which to do User instructs CALO to do both options New mental state S' = (B', {c 1,c 2,c 3,c 4 }, {g 1,g' 2,g 3,g 4 }, {i 1,i' 2 })

Overview CALO: a learning cognitive assistant User delegation of tasks to CALO Delegative BDI agent framework Goal adoption and commitments Summary and research issues

Summary CALO acts as user’s intelligent assistant Classical BDI framework inadequate Implemented BDI systems lack formal grounding Proposed delegative BDI agent framework Separate Desires and Goals Separate Candidate and Adopted Goals Incorporate user guidance and preferences Combined commitment deliberation for goal adoption and intention reconsideration Enables reasoning necessary for an agent such as CALO Implemented by extending SPARK agent framework

Related Work BOID framework [Broersen et al] Different types of agents based on B/D/G/I conflict resolution strategies BDGI CTL logic [Dastani et al] Merging desires into goals Intention reconsideration [Schut et al] Collaborative problem solving [Leveque and Cohen; Allen and Ferguson] Social norms and obligations [Dignum et al]

Future Work Extend goal reasoning to consider resource feasibility (in progress) Proactive goal anticipation and adoption Collaborative human-CALO problem solving Beyond (merely) completing user-delegated tasks Multi-CALO coordination and teamwork Learning as part of CALO’s extended life-cycle More information: