Human-Aware AI (aka Darned Humans: Can’t Live with them. Can’t Live without them) Subbarao Kambhampati Arizona State University Given at U.

Download Report

Transcript Human-Aware AI (aka Darned Humans: Can’t Live with them. Can’t Live without them) Subbarao Kambhampati Arizona State University Given at U.

Human-Aware AI (aka Darned Humans:

Can’t Live with them. Can’t Live without them) Subbarao Kambhampati Arizona State University

Given at U. Washington on 11/2/2007

51 year old field of unknown gender; Birth date unclear; Mother unknown; Many purported fathers; Constantly confuses holy grail with daily progress; Morose disposition

So let’s see if the future is going in quite the right direction…

What is missing in this picture?

Environment (Static vs. Dynamic ) (Observable vs.

Partially Observable ) (perfect vs. Imperfect ) (Full vs. Partial satisfaction ) Goals

A: A Unified Brand-name-Free Introduction to Planning

(Instantaneous vs. Durative ) (Deterministic vs. Stochastic ) What action next?

Subbarao Kambhampati

What is missing in this picture?

Environment (Static vs. Dynamic ) (Observable vs.

Partially Observable ) (perfect vs. Imperfect ) tion per (Full vs. Partial satisfaction ) Goals

A : A U nified Brand-name-Free I ntroduction to Planning

(Instantaneous vs. Durative ) ac tion (Deterministic vs. Stochastic ) What action next? Th e $$$ $$$ Q ue sti on

Subbarao Kambhampati

AI’s Curious Ambivalence to humans..

• Our systems seem happiest – either far away from humans – or in an adversarial stance with humans

You want to help humanity, it is the people that you just can’t stand…

What happened to Co-existence?

• Whither McCarthy’s advice taker?

• ..or Janet Kolodner’s house wife?

• …or even Dave’s HAL? • (with hopefully a less sinister voice)

Why aren’t we doing HAAI?

• ..to some extent we are – Assistive technology; Intelligent user interfaces; Augmented cognition, Human-Robot Interaction – But it is mostly smuggled under the radar..

– And certainly doesn’t get no respect..

• Rodney Dangerfield of AI?

• Is it time to bring it to the center stage?

– Having them as applied side of AI makes them seem peripheral, and little formal attention gets paid to them by the “main-stream”

(Some) Challenges of HAAI

• Communication – Human-level communication/interfacing • Need to understand what makes natural interfaces..

– Explanations • Humans want explanations (even if fake..) • Teachability – Advice Taking (without lobotomy) • Elaboration tolerance – Dealing with evolving models • You rarely tell everything at once to your secretary..

– Need to operate in an “any-knowledge” mode • Recognizing Human’s state – Recognizing intent; activity – Detecting/handling emotions/affect

Caveats & Worries about HAAI

• Are any of these challenges really new?

• HAAI vs. HDAI (human-dependent AI) – Human dependent AI can be enormously lucrative if you find the right sweet spot.. • But will it hamper eventual progress to (HA)AI?

• Advice taking can degenerate to advice needing..

• Designing HAAI agents may need competence beyond computer science..

Are the challenges really new? Are they too hard?

• Isn’t any kind of feedback “advice giving”? Isn’t reinforcement learning already foregrounding “evolving domain models” – A question of granularity. There is no need to keep the interactions mono-syllabic..

• Won’t communication require NLP and thus become AI complete?

– There could well be a spectrum of communication modalities that could be tried • Doesn’t recognition of human activity/emotional state really AI?

– ..it is if we want HAAI (you want to work with humans, you need to have some idea of their state..)

HDAI: Finding“Sweet Spots” in computer-mediated cooperative work

• It is possible to get by with techniques blithely ignorant of semantics, when you have humans in the loop – All you need is to find the right sweet spot, where the computer plays a pre-processing role and presents “potential solutions” – …and the human very gratefully does the in-depth analysis on those few potential solutions • Examples: – The incredible success of “Bag of Words” model! • Bag of letters would be a disaster ;-) • Bag of sentences and/or NLP would be good – ..but only to your discriminating and irascible searchers ;-) • Concern: – Will pursuit of HDAI inhibit progress towards eventual AI? • By inducing perpetual dependence on (rather than awareness of) the human in the loop?

Delusions of Advice Taking: Give me Advice that I can easily use

• Planners that expect “advice” that is expressed in terms of their internal choice points – HSTS, a NASA planner, depended on this type of knowledge.. • Learners that expect “advice” that can be easily included into their current algorithm – “Must link”/ “Must-not Link” constraints used in “semi-supervised” clustering algorithms Moral: It is wishful to expect advice that will be tailored to your program internals.

Operationalizing high-level advice

is

your (AI program’s) responsibility

HAAI pushes us beyond CS…

• By dubbing “acting rational” as the definition of AI, we carefully separated the AI enterprise from “psychology”, “cognitive science” etc.

• But pursuit of HAAI pushes us right back into these disciplines (and more) – Making an interface that improves interaction with humans requires understanding of human psychology..

• E.g. studies showing how programs that have even a rudimentary understanding of human emotions fare much better in interactions with humans • Are we ready to do HAAI despite this push beyond comfort zone?

How are sub-areas doing on HAAI?

I’ll focus on “teachability” aspect in two areas that I know something about – Full autonomy through complete domain models – Can take prior knowledge in the form of • Domain physics – Full autonomy through tabula rasa learning over gazillion samples – Seems incapable of taking much prior knowledge • Unless sneaked in through features and kernels..

What’s Rao doing in HAAI?

• Model-lite planning • Planning in HRI scenarios • Human-aware information integration (Some) Challenges of HAAI • Communication – Human-level communication/interfacing • Need to understand what makes natural interfaces..

– Explanations • Humans want explanations (even if fake..) • Teachability – Advice Taking (without lobotomy) • Elaboration tolerance – Dealing with evolving models • You rarely tell everything at once to your secretary..

– Need to operate in an “any-knowledge” mode • Recognizing Human’s state – Recognizing intent; activity – Detecting/handling emotions/affect

Motivations for Model-lite

Is the only way to get more applications is to tackle more and more expressive domains?

• There are many scenarios where domain modeling is the biggest obstacle – Web Service Composition • Most services have very little formal models attached – Workflow management • Most workflows are provided with little information about underlying causal models – Learning to plan from demonstrations • We will have to contend with incomplete and evolving domain models..

• ..but our approaches assume complete and correct models..

Model-Lite Planning is

From “Any Time” to “Any Model”

Planning with incomplete models

Planning • ..“incomplete”  “not enough domain knowledge to verify correctness/optimality” • How

incomplete

is incomplete?

• Knowing no more than I/O types?

• Missing a couple of preconditions/effects or user preferences?

Challenges in Realizing Model-Lite Planning

1. Planning support for shallow domain models [ICAC 2005] 2. Plan creation with approximate domain models [IJCAI 2007, ICAPS Wkshp 2007] 3. Learning to improve completeness of domain models [ICAPS Wkshp 2007]

Challenge: Planning Support for Shallow Domain Models

• Provide planning support that exploits the shallow model available • Idea: Explore wider variety of domain knowledge that can either be easily specified interactively or learned/mined. E.g. • I/O type specifications (e.g. Woogle) • Task Dependencies (e.g. workflow specifications) – Qn: Can these be compiled down to a common substrate?

• Types of planning support that can be provided with such knowledge – Critiquing plans in mixed-initiative scenarios – Detecting incorrectness (as against verifying correctness)

Challenge: Plan Creation with Approximate Domain Models

• Support plan creation despite missing details in the model. The missing details may be (1) action models (2) cost/utility models • Example: Generate robust “line” plans in the face of incompleteness of action description – View model incompleteness as a form of uncertainty (e.g. work by Amir et. al.) • Example: Generate Diverse/Multi-option plans in the face of incompleteness of cost model – Our IJCAI-2007 work can be viewed as being motivated this way..

Note: Model-lite planning aims to reduce the modeling burden; the planning itself may actually be harder

Imprecise Intent & Diversity

Challenge: Learning to Improve Completeness of Domain Models

• In traditional “model-intensive” planning learning is mostly motivated for speedup – ..and it has gradually become less and less important with the advent of fast heuristic planners • In model-lite planning, learning (also) helps in model acquisition and – Learning from a variety of sources • Textual descriptions; plan traces; expert demonstrations – Learning in the presence of background knowledge • The current model serves as background knowledge for additional refinements for learning • Example efforts etc. model refinement. – Much of DARPA IL program (including our LSP system); PLOW – Stochastic Explanation-based Learning (ICAPS 2007 wkhop) Make planning Model-lite  Make learning knowledge (model) rich

• •

Learning & Planning with incomplete models: A proposal..

Represent incomplete domain with (relational) probabilistic logic – Weighted precondition axiom – Weighted effect axiom – Weighted static property axiom Domain Model - Blocksworld • • • • • • • • 0.9, Pickup (x) -> armempty() 1, Pickup (x) -> clear(x) 1, Pickup (x) -> ontable(x) 0.8, Pickup (x) –> holding(x) 0.8, Pickup (x) -> not armempty() 0.8, Pickup (x) -> not ontable(x) 1, Holding (x) -> not armempty() 1, Holding (x) -> not ontable(x) Precondition Axiom: Relates Actions with Current state facts Effect Axiom: Relates Actions with Next state facts Static Property: Relates Facts in a State Address learning and planning problem – Learning involves • Updating the prior weights on the axioms • Finding new axioms – Planning involves • Probabilistic planning in the presence of precondition uncertainty • Consider using MaxSat to solve problems in the proposed formulation Can we view the probabilistic plangraph as Bayes net?

A B Domain Static Property Can be asserted too, 0.9

0.5

A B

clear_a clear_b armempty ontable_a ontable_b pickup_a

pickup_b noop_clear_a

noop_clear_b

noop_armempty noop_ontable_a

noop_ontable_b

0.8

clear_a

clear_b

armempty ontable_a

ontable_b holding_a

holding_b pickup_a pickup_b

stack_a_b

stack_b_a noop_clear_a noop_clear_b noop_armempty noop_ontable_a noop_ontable_b noop_holding_a noop_holding_b Evidence Variables How we find a solution?

MPE (most probabilistic explanation) There are some solvers out there 0.8

Towards Model-lite Planning - Sungwook Yoon

clear_a clear_b armempty ontable_a ontable_b holding_a holding_b

on_a_b

on_b_a

Indiana Univ; ASU Stanford, Notre Dame MURI 2007: Effective Human-Robot Interaction under Time Pressure

[CIDR 07; VLDB 07]

Challenges in Querying Autonomous Databases Imprecise Queries

User’s needs are not clearly defined hence: 

Queries may be too general

Queries may be too specific Incomplete Data

Databases are often populated by: 

Lay users entering data

Automated extraction

Relevance Function Density Function General Solution:

“Expected Relevance Ranking”

Challenge: Automated & Non-intrusive assessment of Relevance and Density functions However, how can we retrieve similar/ incomplete tuples in the first place?

Challenge: Rewriting a user’s query to retrieve highly relevant Similar/ Incomplete tuples Once the similar/incomplete tuples have been retrieved, why should users believe them?

Challenge: Provide explanations for the uncertain answers in order to gain the user’s trust

QUIC: Handling Query Imprecision & Data Incompleteness in Autonomous Databases

Summary:

Say Hi to HAAI

• We may want to take HAAI as seriously as we take autonomous agency – My argument is not that everybody should do it, but rather that it should be seen as “main stream” rather than as some applied • HAAI does emphasize specific technical challenges: Communication; Teachability; Human state recognition • Pursuit of HAAI involves pitfalls (e.g. need to differentiate HDAI and HAAI) as well as a broadening of focus (e.g. need to take interface issues seriously) • Some steps towards HAAI in planning

Points to Ponder..

• Do we (you) agree that we might need human-aware AI? • Do you think anything needs to change in your current area of interest as a consequence?

• (What)(Are there) foundational problems in human-aware AI?

– Is HAAI moot without full NLP?

• How do we make progress towards HAAI – Is IUI considered progress towards HAAI?

– Is model-lite planning?

– Is learning by X (X= “demonstrations”; “being told”…)?

– Is elicitation of utility models/recognition of intent?

(Some) Challenges of HAAI • Communication – Human-level communication/interfacing • Need to understand what makes natural interfaces..

– Explanations • Humans want explanations (even if fake..) • Teachability – Advice Taking (without lobotomy) • Elaboration tolerance – Dealing with evolving models • You rarely tell everything at once to your secretary..

– Need to operate in an “any-knowledge” mode • Recognizing Human’s state – Recognizing intent; activity – Detecting/handling emotions/affect

Epilogue: HAAI is Hard but Needed..

• The challenges posed by HAAI may take us out of the carefully circumscribed goals of AI • Given a choice, us computer scientists would rather not think about messy human interactions..

• But, do we really have a choice?