10
Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal Lesh, Kathy Ryall, Charles Rich, Candy Sidner Carnegie Mellon University, 2001

Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

Embed Size (px)

Citation preview

Page 1: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

Task Learning in COLLAGEN

The COLLAGEN Architecture; Task Learning from Demonstrations

Work @: Mitshubishi Electric Research LabsAndrew Garland, Neal Lesh, Kathy Ryall, Charles Rich,Candy Sidner

Carnegie Mellon University, 2001

Page 2: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 2

Outline The COLLAGEN Architecture:

P1: COLLAGEN: Applying Collaborative Discourse Theory to Human-Computer Interaction

Learning Task Models: P2: Learning Task Models from Collaborative Discourse

Add refinement & regression testing: P3: Learning Hierarchical Task Models by Defining and Refining Examples

Adding guessers: P4: Interactively Defining Examples to be Generalized

Discussion: pros, cons, questions …

Page 3: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 3

COLLAGEN COLLAGEN = COLLaborative AGENt Based on SharedPlans discourse theory (Grosz &

Sidner) Not the classical dialog-system view: agent &

human collaborate, and they both interact with the application

4 agents presented: VCR, SymbolEditor, GasTurbine agent, home thermostat (kind-of toy domains)

Page 4: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 4

COLLAGEN (cont’d)

Dialog Management architecture Discourse state

Focus stack (stack of goals) Plan tree for each of them

Actions: primitive / non-primitive Recipes = specification of goal decompositions

Partially ordered steps, parameters, constraints, pre- and post-conditions

Updating the discourse state: 5 cond… Plan recognition

Page 5: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 5

Learning Task Models from Collaborative Discourse [2] Starting Point: “more difficult for people to deal

with abstractions in the task than to generate and discuss examples”

“Programming-by-Demonstration” approach: Infer task models from partially-annotated examples of

task behavior.

Similarities with Helpdesk Call Center … CallCenter idea: learn from watching traffic

Richly annotate traffic / recent EARS stuff… Learn task structure from annotated traffic

Page 6: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 6

Learning Task Models (cont’d) Annotation Language:

e, S, optional, unordered, unequal Q: how powerful is this task representation ?

fully annotating would be burdensome

Learning: alignment, optionals, orders & propagators

BIAS for learning … Alignment: Disjoint step assumption Alignment: Step type assumption.

Q: Hmm, not sure I got this…

Propagators: Suggested parameter preference bias (~ occam’s razor)

Page 7: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 7

Learning Task Models – Experiments. How:

Start from 2 task models Generate examples, randomize Relearn models, see what you get…

Results: Optional did not get much action: it figures, it’s probably

the easiest to learn… Equality seems to buy a lot; and this is good ! Learning is strongly influenced by the order of

examples…

Discussion Not adequate for direct use * Mention of the “online” flavor

Page 8: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 8

Learning HTN by defining and refining examples Created a development environment which

integrates the learning techniques with: Defining & Refining examples Regression testing (needed if manual edits are allowed)

They esentially give a management process for the development of task models [fig. 3]

Q: Is there any reason for Starting Set of Actions ? Q: The whole things looks really like a storyboard, but is

there anything really new here ?

Page 9: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 9

Interactively Defining Examples to be Generalized NEW: Guessers Guessers suggest to the user what annotations

might be helpful Organized in committees to improve robustness;* Knowledge sources:

Other examples * Current generalization The inference techniques ~ active learning Raw data Domain Theory Heuristics

Page 10: Task Learning in COLLAGEN The COLLAGEN Architecture; Task Learning from Demonstrations Work @: Mitshubishi Electric Research Labs Andrew Garland, Neal

11-04-01 Modeling the cost of misunderstanding … 10

So what do you think ? Is it worth it ? When ? Does the conjecture hold ? How about when you collect the examples ? (ala

CallCenter)