Scaling up Partially Observable Markov Decision Processes for Dialogue Management
|
|
- Laura Karin Mathews
- 6 years ago
- Views:
Transcription
1 Scaling up Partially Observable Markov Decision Processes for Dialogue Management Jason D. Williams 22 July 2005 Machine Intelligence Laboratory Cambridge University Engineering Department
2 Outline Dialogue management as a POMDP Scaling up with the summary POMDP method Example problem & results Conclusions & future work Material in this talk is joint work with Steve Young Jason D. Williams, Pascal Poupart, and Steve Young (2005). Factored Partially Observable Markov Decision Processes for Dialogue Management. 4th Workshop on Knowledge and Reasoning in Practical Dialog Systems, International Joint Conference on Artificial Intelligence (IJCAI), August 2005, Edinburgh. Jason D. Williams, Pascal Poupart, and Steve Young (2005). Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management. In Proceedings of the 6th SigDial Workshop on Discourse and Dialogue, September 2005, Lisbon.
3 Idealized Human-Computer Dialog Boston to London I want to go to London to=london Boston to London From Boston from=austin to=stated from=null Where from? to=stated from=stated When? Current state = dialogue modelling System action selection = dialogue management Dialogue state is unobserved: User s goal User s (real) action Conversation state Inferences via observation: May contain errors
4 Decompose state variable into 3 models user goal Time t Time t+1 S u dialogue state S u A u user action S d r Reward A u S d O A s system action O observation B B belief state Designer specifies r; mapping A s = Π( b( S)) seeks to maximize cumulative reward
5 A policy as a partitioning A policy is a mapping: situation action One representation is a partitioning of belief space 2-dimensional example: Simple state space with 2 user goals: A & B Belief space can be written as b(a) (b/c b(b) = 1 - b(a)) Policy shows action to take for each point in belief space Belief state: b(a)=0.0 b(a)=0.5 b(a)=1.0 System action: submit(b) confirm(b) ask-a-or-b confirm(a) submit(a) A s = Π( b( S)) This partitioning is produced by a POMDP optimization method
6 Outline Dialogue management as a POMDP Scaling up with the summary POMDP method Example problem & results Conclusions & future work
7 POMDPs scale poorly Belief space, actions, and observations cover N slots and M slot values i M S u A u A s O london london, to(london) conf(london), submit(london) london, to(london) leeds leeds, to(leeds) conf(leeds), submit(leeds) leeds, to(leeds)......, to(...) conf(...), submit(...)..., to(...) dover dover, to(dover) conf(dover), submit(dover) dover, to(dover) For M=1000 and N=2, there are ~10 6 states, actions, and observations N Growth factor is O(M N ) Can perform belief monitoring with factoring, but how to optimize?
8 Intuition of the Summary POMDP b( s u ) london leeds bath b ~ s ( u ) best rest b( a u ) tolondon london toleeds b( s d ) b ~ s ( d ) notstated stated confirmed notstated stated confirmed ~ ~ S A S = S u S = 2 3 u u d d
9 Actions in the summary POMDP a ask a ~ ask confirm(london) confirm(leeds) confirm(dover) M 1 confirm(x) x = arg max( b( s u )) submit(london) submit(leeds) submit(dover) M 1 submit(x) x = arg max( b( s u ))
10 Observations in the summary POMDP Observations in summary POMDP give an compact indication of how is changing based on s and o. It has 2 parts. b(s ~ ) arg max( b ( s o ~1 u)) == arg max( b( s ))? { same, different u } s s o Is o~ 2 arg max( b( s )) consistent with o? consistent inconsistent no info u
11 Summary POMDP method 1 p ( s s, a) p ( o s, a) r( s, a) sample p ( ~ s ~ s, a~ ) p ( o~ ~ s, a~ ) r( ~ s, a~ ) 2 3 p ( ~ s ~ s, a~ ) p ( o~ ~ s, a~ ) r( ~ s, a~ ) run maintain b(s) optimize π ( b( ~ s )) b( ~ sd ) b( sd ) b( ~ su ) max( b( su )) a ~ π ( b( ~ )) a a~ s,arg max( b( s ))) ( u
12 Outline Dialogue management as a POMDP Scaling up with the summary POMDP method Example problem & results Conclusions & future work
13 1000-place dialog problem User is travelling from x to y in a world with 1000 cities s u : The user s desired from and to cities e.g., (a,b) a u, o : yes, no, null, a, from(a), to(a), {from(a),to(b)}, etc. s d : Each slot can be not stated, unconfirmed, or confirmed a s : ask-from, ask-to, conf-from(a), conf-to(b), submit(a,b) User goal model: User has a fixed goal throughout the dialogue User action model: Estimated from real dialogue data Conversation model: Deterministically promotes slots Speech recognition model : Substitutions & del s with prob. p err Reward fn : +50 correct submit, -50 wrong submit, -5 fail, -3 for confirming something which is not stated, etc., -1 per-turn otherwise Solve with Perseus (PBVI)
14 Simulated speech recognition channel 2 subjects interact through a simulated speech recognition channel End-pointer Typist Wizard ASR-noise generator Typical end-pointing model Subject Wizard talks into microphone Wizard s screen shows corrupted input Utterances are transcribed by a typist Confusions generated using lexicon, phonetic confusion matrix, and language model Matthew Stuttle, Jason D. Williams, and Steve Young. A Framework for Wizard-of- Oz Experiments with a Simulated ASR-Channel. ICSLP, 2004, South Korea.
15 SACTI-1 dialog data corpus Tourist information domain Wizard has more info than user; user given specific task Fountain H1 R2 H5 Fountain Road R4 H4 Main square North Road Art Square Cinema R6 Middle Road Nine street Castle Castle Loop H2 Castle Loop B6 36 users / 12 wizards 144 dialogs 4071 turns 4 different WER targets Task completion Likert-scale questions West loop Shopping area Alexander Street Tower Hill Road Tower R1 B1 B5 Tourist info Alexander Street B4 Post office B2 B3 H6 Main Street Alexander Street Red Bridge South Bridge Bridge Nine Riverside Drive R3 Park Road Museum Cascade Road H3 Park R5 Conversational characteristics broadly similar to those observed in human/machine dialog. Jason D. Williams and Steve Young. Characterizing Task-Oriented Dialog using a Simulated ASR Channel. ICSLP, 2004, South Korea.
16 User model example S u A s WH a to YN a to WH a from YN a from London To London null yes no null Oxford From Oxford null yes no null P(A u -WH A s, S u =to(london)) A s Where are you going to? To London, is that right? Where are you going from? P mass of A u ( to/wh portion only) London To London null Data was divided, and two model sets were created: Training model set & Testing model set
17 Turn b ( s slot from ) b ( ~ s from ) b ( s slot to ) b ( ~ ) [prior to start of dialog] CAMB. SHEFF. ~ slot LEEDS OXFORD ~ s slot to Where to? London [Leeds] CAMB. SHEFF. LEEDS OXFORD Where from? From Cambridge [To Oxford] CAMB. SHEFF. LEEDS OXFORD Where from? From Cambridge [From Cambridge] CAMB. SHEFF. LEEDS OXFORD To Leeds, right? No, to London [No, from Sheffield] CAMB. SHEFF. LEEDS OXFORD Where to? London from Cambridge [London from Cambridge] CAMB. SHEFF. LEEDS OXFORD
18 Performance vs. p err User model built from training set p err Reward gained / turn
19 Performance vs. p err User model built from training set User model built from test set p err Reward gained / turn
20 Scalability vs. direct optimization Summary POMDP Baseline Average or expected return M (Number of distinct slot values)
21 Outline Dialogue management as a POMDP Scaling up with the summary POMDP method Example problem & results Conclusions & future work
22 Conclusions & future work For slot-based dialog management, POMDPs Outperform MDP baseline Outperform 3 handcrafted baselines Can be scaled as a summary POMDP to many slot values Interesting future avenues Scale number of slots to 10s Move beyond slot-based approaches Apply to real system
23 Thanks! Jason D. Williams Joint work with Steve Young
Recent Developments in Statistical Dialogue Systems
Recent Developments in Statistical Dialogue Systems Steve Young Machine Intelligence Laboratory Information Engineering Division Cambridge University Engineering Department Cambridge, UK Contents Review
More informationPoint-Based Value Iteration for Constrained POMDPs
Point-Based Value Iteration for Constrained POMDPs Dongho Kim Jaesong Lee Kee-Eung Kim Department of Computer Science Pascal Poupart School of Computer Science IJCAI-2011 2011. 7. 22. Motivation goals
More informationDialogue as a Decision Making Process
Dialogue as a Decision Making Process Nicholas Roy Challenges of Autonomy in the Real World Wide range of sensors Noisy sensors World dynamics Adaptability Incomplete information Robustness under uncertainty
More informationTopics of Active Research in Reinforcement Learning Relevant to Spoken Dialogue Systems
Topics of Active Research in Reinforcement Learning Relevant to Spoken Dialogue Systems Pascal Poupart David R. Cheriton School of Computer Science University of Waterloo 1 Outline Review Markov Models
More informationOn Prediction and Planning in Partially Observable Markov Decision Processes with Large Observation Sets
On Prediction and Planning in Partially Observable Markov Decision Processes with Large Observation Sets Pablo Samuel Castro pcastr@cs.mcgill.ca McGill University Joint work with: Doina Precup and Prakash
More informationDialogue management: Parametric approaches to policy optimisation. Dialogue Systems Group, Cambridge University Engineering Department
Dialogue management: Parametric approaches to policy optimisation Milica Gašić Dialogue Systems Group, Cambridge University Engineering Department 1 / 30 Dialogue optimisation as a reinforcement learning
More informationRL 14: Simplifications of POMDPs
RL 14: Simplifications of POMDPs Michael Herrmann University of Edinburgh, School of Informatics 04/03/2016 POMDPs: Points to remember Belief states are probability distributions over states Even if computationally
More informationSPOKEN dialog systems (SDSs) help people accomplish
IEEE TRANS. ON AUDIO, SPEECH & LANGUAGE PROCESSING, VOL.???, NO.???, MONTH??? YEAR??? 1 Scaling POMDPs for spoken dialog management Astract Control in spoken dialog systems is challenging largely ecause
More informationDialogue Systems. Statistical NLU component. Representation. A Probabilistic Dialogue System. Task: map a sentence + context to a database query
Statistical NLU component Task: map a sentence + context to a database query Dialogue Systems User: Show me flights from NY to Boston, leaving tomorrow System: [returns a list of flights] Origin (City
More informationSymbolic Perseus: a Generic POMDP Algorithm with Application to Dynamic Pricing with Demand Learning
Symbolic Perseus: a Generic POMDP Algorithm with Application to Dynamic Pricing with Demand Learning Pascal Poupart (University of Waterloo) INFORMS 2009 1 Outline Dynamic Pricing as a POMDP Symbolic Perseus
More informationPlanning Under Uncertainty II
Planning Under Uncertainty II Intelligent Robotics 2014/15 Bruno Lacerda Announcement No class next Monday - 17/11/2014 2 Previous Lecture Approach to cope with uncertainty on outcome of actions Markov
More informationTowards Uncertainty-Aware Path Planning On Road Networks Using Augmented-MDPs. Lorenzo Nardi and Cyrill Stachniss
Towards Uncertainty-Aware Path Planning On Road Networks Using Augmented-MDPs Lorenzo Nardi and Cyrill Stachniss Navigation under uncertainty C B C B A A 2 `B` is the most likely position C B C B A A 3
More informationReinforcement Learning and NLP
1 Reinforcement Learning and NLP Kapil Thadani kapil@cs.columbia.edu RESEARCH Outline 2 Model-free RL Markov decision processes (MDPs) Derivative-free optimization Policy gradients Variance reduction Value
More informationAn Introduction to Markov Decision Processes. MDP Tutorial - 1
An Introduction to Markov Decision Processes Bob Givan Purdue University Ron Parr Duke University MDP Tutorial - 1 Outline Markov Decision Processes defined (Bob) Objective functions Policies Finding Optimal
More informationArtificial Intelligence & Sequential Decision Problems
Artificial Intelligence & Sequential Decision Problems (CIV6540 - Machine Learning for Civil Engineers) Professor: James-A. Goulet Département des génies civil, géologique et des mines Chapter 15 Goulet
More informationMarkov Models and Reinforcement Learning. Stephen G. Ware CSCI 4525 / 5525
Markov Models and Reinforcement Learning Stephen G. Ware CSCI 4525 / 5525 Camera Vacuum World (CVW) 2 discrete rooms with cameras that detect dirt. A mobile robot with a vacuum. The goal is to ensure both
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2011 Lecture 12: Probability 3/2/2011 Pieter Abbeel UC Berkeley Many slides adapted from Dan Klein. 1 Announcements P3 due on Monday (3/7) at 4:59pm W3 going out
More informationCS 188: Artificial Intelligence Fall 2011
CS 188: Artificial Intelligence Fall 2011 Lecture 20: HMMs / Speech / ML 11/8/2011 Dan Klein UC Berkeley Today HMMs Demo bonanza! Most likely explanation queries Speech recognition A massive HMM! Details
More informationInverse Reinforcement Learning in Partially Observable Environments
Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI-09) Inverse Reinforcement Learning in Partially Observable Environments Jaedeug Choi and Kee-Eung Kim Department
More informationIntroduction to Sequential Teams
Introduction to Sequential Teams Aditya Mahajan McGill University Joint work with: Ashutosh Nayyar and Demos Teneketzis, UMichigan MITACS Workshop on Fusion and Inference in Networks, 2011 Decentralized
More informationKnowledge Extraction from DBNs for Images
Knowledge Extraction from DBNs for Images Son N. Tran and Artur d Avila Garcez Department of Computer Science City University London Contents 1 Introduction 2 Knowledge Extraction from DBNs 3 Experimental
More informationLecture 3: ASR: HMMs, Forward, Viterbi
Original slides by Dan Jurafsky CS 224S / LINGUIST 285 Spoken Language Processing Andrew Maas Stanford University Spring 2017 Lecture 3: ASR: HMMs, Forward, Viterbi Fun informative read on phonetics The
More informationIntelligent Systems (AI-2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 19 Oct, 23, 2015 Slide Sources Raymond J. Mooney University of Texas at Austin D. Koller, Stanford CS - Probabilistic Graphical Models D. Page,
More informationAn Analytic Solution to Discrete Bayesian Reinforcement Learning
An Analytic Solution to Discrete Bayesian Reinforcement Learning Pascal Poupart (U of Waterloo) Nikos Vlassis (U of Amsterdam) Jesse Hoey (U of Toronto) Kevin Regan (U of Waterloo) 1 Motivation Automated
More informationTemporal Difference Learning & Policy Iteration
Temporal Difference Learning & Policy Iteration Advanced Topics in Reinforcement Learning Seminar WS 15/16 ±0 ±0 +1 by Tobias Joppen 03.11.2015 Fachbereich Informatik Knowledge Engineering Group Prof.
More informationChristopher Watkins and Peter Dayan. Noga Zaslavsky. The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015
Q-Learning Christopher Watkins and Peter Dayan Noga Zaslavsky The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015 Noga Zaslavsky Q-Learning (Watkins & Dayan, 1992)
More informationThe SJTU System for Dialog State Tracking Challenge 2
The SJTU System for Dialog State Tracking Challenge 2 Kai Sun, Lu Chen, Su Zhu and Kai Yu Department of Computer Science and Engineering, Shanghai Jiao Tong University Shanghai, China {accreator, chenlusz,
More informationExperiments with a Gaussian Merging-Splitting Algorithm for HMM Training for Speech Recognition
Experiments with a Gaussian Merging-Splitting Algorithm for HMM Training for Speech Recognition ABSTRACT It is well known that the expectation-maximization (EM) algorithm, commonly used to estimate hidden
More informationIntelligent Systems (AI-2)
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 19 Oct, 24, 2016 Slide Sources Raymond J. Mooney University of Texas at Austin D. Koller, Stanford CS - Probabilistic Graphical Models D. Page,
More informationRL 14: POMDPs continued
RL 14: POMDPs continued Michael Herrmann University of Edinburgh, School of Informatics 06/03/2015 POMDPs: Points to remember Belief states are probability distributions over states Even if computationally
More informationMarkov Logic Networks for Spoken Language Interpretation
Intelligent Information Systems 9999 ISBN 666-666-666, pages 1 10 Markov Logic Networks for Spoken Language Interpretation Marie-Jean Meurs, Frédéric Duvert, Fabrice Lefèvre, and Renato De Mori Université
More informationDon t Plan for the Unexpected: Planning Based on Plausibility Models
Don t Plan for the Unexpected: Planning Based on Plausibility Models Thomas Bolander, DTU Informatics, Technical University of Denmark Joint work with Mikkel Birkegaard Andersen and Martin Holm Jensen
More informationIntroduction to Artificial Intelligence (AI)
Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 10 Oct, 13, 2011 CPSC 502, Lecture 10 Slide 1 Today Oct 13 Inference in HMMs More on Robot Localization CPSC 502, Lecture
More informationPlanning by Probabilistic Inference
Planning by Probabilistic Inference Hagai Attias Microsoft Research 1 Microsoft Way Redmond, WA 98052 Abstract This paper presents and demonstrates a new approach to the problem of planning under uncertainty.
More informationKalman Based Temporal Difference Neural Network for Policy Generation under Uncertainty (KBTDNN)
Kalman Based Temporal Difference Neural Network for Policy Generation under Uncertainty (KBTDNN) Alp Sardag and H.Levent Akin Bogazici University Department of Computer Engineering 34342 Bebek, Istanbul,
More informationMarkov decision processes (MDP) CS 416 Artificial Intelligence. Iterative solution of Bellman equations. Building an optimal policy.
Page 1 Markov decision processes (MDP) CS 416 Artificial Intelligence Lecture 21 Making Complex Decisions Chapter 17 Initial State S 0 Transition Model T (s, a, s ) How does Markov apply here? Uncertainty
More information1 [15 points] Search Strategies
Probabilistic Foundations of Artificial Intelligence Final Exam Date: 29 January 2013 Time limit: 120 minutes Number of pages: 12 You can use the back of the pages if you run out of space. strictly forbidden.
More informationDiscrete Probability and State Estimation
6.01, Fall Semester, 2007 Lecture 12 Notes 1 MASSACHVSETTS INSTITVTE OF TECHNOLOGY Department of Electrical Engineering and Computer Science 6.01 Introduction to EECS I Fall Semester, 2007 Lecture 12 Notes
More informationOptimal Control of Partiality Observable Markov. Processes over a Finite Horizon
Optimal Control of Partiality Observable Markov Processes over a Finite Horizon Report by Jalal Arabneydi 04/11/2012 Taken from Control of Partiality Observable Markov Processes over a finite Horizon by
More informationHidden Markov Model and Speech Recognition
1 Dec,2006 Outline Introduction 1 Introduction 2 3 4 5 Introduction What is Speech Recognition? Understanding what is being said Mapping speech data to textual information Speech Recognition is indeed
More informationAdministration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon.
Administration CSCI567 Machine Learning Fall 2018 Prof. Haipeng Luo U of Southern California Nov 7, 2018 HW5 is available, due on 11/18. Practice final will also be available soon. Remaining weeks: 11/14,
More informationFinite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs
Finite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs Christopher Amato Department of Computer Science University of Massachusetts Amherst, MA 01003 USA camato@cs.umass.edu
More informationThe Markov Decision Process Extraction Network
The Markov Decision Process Extraction Network Siegmund Duell 1,2, Alexander Hans 1,3, and Steffen Udluft 1 1- Siemens AG, Corporate Research and Technologies, Learning Systems, Otto-Hahn-Ring 6, D-81739
More informationClassification: Naïve Bayes. Nathan Schneider (slides adapted from Chris Dyer, Noah Smith, et al.) ENLP 19 September 2016
Classification: Naïve Bayes Nathan Schneider (slides adapted from Chris Dyer, Noah Smith, et al.) ENLP 19 September 2016 1 Sentiment Analysis Recall the task: Filled with horrific dialogue, laughable characters,
More informationState Space Abstraction for Reinforcement Learning
State Space Abstraction for Reinforcement Learning Rowan McAllister & Thang Bui MLG, Cambridge Nov 6th, 24 / 26 Rowan s introduction 2 / 26 Types of abstraction [LWL6] Abstractions are partitioned based
More informationINF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018
Machine learning for image classification Lecture 14: Reinforcement learning May 9, 2018 Page 3 Outline Motivation Introduction to reinforcement learning (RL) Value function based methods (Q-learning)
More informationSolving POMDPs with Continuous or Large Discrete Observation Spaces
Solving POMDPs with Continuous or Large Discrete Observation Spaces Jesse Hoey Department of Computer Science University of Toronto Toronto, ON, M5S 3H5 jhoey@cs.toronto.edu Pascal Poupart School of Computer
More informationCS599 Lecture 1 Introduction To RL
CS599 Lecture 1 Introduction To RL Reinforcement Learning Introduction Learning from rewards Policies Value Functions Rewards Models of the Environment Exploitation vs. Exploration Dynamic Programming
More informationCS 188: Artificial Intelligence Spring Today
CS 188: Artificial Intelligence Spring 2006 Lecture 9: Naïve Bayes 2/14/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Bayes rule Today Expectations and utilities Naïve
More informationOutline. CSE 573: Artificial Intelligence Autumn Agent. Partial Observability. Markov Decision Process (MDP) 10/31/2012
CSE 573: Artificial Intelligence Autumn 2012 Reasoning about Uncertainty & Hidden Markov Models Daniel Weld Many slides adapted from Dan Klein, Stuart Russell, Andrew Moore & Luke Zettlemoyer 1 Outline
More informationLecture 14. Clustering, K-means, and EM
Lecture 14. Clustering, K-means, and EM Prof. Alan Yuille Spring 2014 Outline 1. Clustering 2. K-means 3. EM 1 Clustering Task: Given a set of unlabeled data D = {x 1,..., x n }, we do the following: 1.
More informationThe Noisy Channel Model and Markov Models
1/24 The Noisy Channel Model and Markov Models Mark Johnson September 3, 2014 2/24 The big ideas The story so far: machine learning classifiers learn a function that maps a data item X to a label Y handle
More informationOpen Problem: Approximate Planning of POMDPs in the class of Memoryless Policies
Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies Kamyar Azizzadenesheli U.C. Irvine Joint work with Prof. Anima Anandkumar and Dr. Alessandro Lazaric. Motivation +1 Agent-Environment
More informationMathematical Formulation of Our Example
Mathematical Formulation of Our Example We define two binary random variables: open and, where is light on or light off. Our question is: What is? Computer Vision 1 Combining Evidence Suppose our robot
More informationProf. Dr. Ann Nowé. Artificial Intelligence Lab ai.vub.ac.be
REINFORCEMENT LEARNING AN INTRODUCTION Prof. Dr. Ann Nowé Artificial Intelligence Lab ai.vub.ac.be REINFORCEMENT LEARNING WHAT IS IT? What is it? Learning from interaction Learning about, from, and while
More informationSeq2Seq Losses (CTC)
Seq2Seq Losses (CTC) Jerry Ding & Ryan Brigden 11-785 Recitation 6 February 23, 2018 Outline Tasks suited for recurrent networks Losses when the output is a sequence Kinds of errors Losses to use CTC Loss
More informationSymbolic Dynamic Programming for Continuous State and Observation POMDPs
Symbolic Dynamic Programming for Continuous State and Observation POMDPs Zahra Zamani ANU & NICTA Canberra, Australia zahra.zamani@anu.edu.au Pascal Poupart U. of Waterloo Waterloo, Canada ppoupart@uwaterloo.ca
More informationCS 570: Machine Learning Seminar. Fall 2016
CS 570: Machine Learning Seminar Fall 2016 Class Information Class web page: http://web.cecs.pdx.edu/~mm/mlseminar2016-2017/fall2016/ Class mailing list: cs570@cs.pdx.edu My office hours: T,Th, 2-3pm or
More informationSum-Product Networks. STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 17, 2017
Sum-Product Networks STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 17, 2017 Introduction Outline What is a Sum-Product Network? Inference Applications In more depth
More informationOptimally Solving Dec-POMDPs as Continuous-State MDPs
Optimally Solving Dec-POMDPs as Continuous-State MDPs Jilles Dibangoye (1), Chris Amato (2), Olivier Buffet (1) and François Charpillet (1) (1) Inria, Université de Lorraine France (2) MIT, CSAIL USA IJCAI
More informationToday s Outline. Recap: MDPs. Bellman Equations. Q-Value Iteration. Bellman Backup 5/7/2012. CSE 473: Artificial Intelligence Reinforcement Learning
CSE 473: Artificial Intelligence Reinforcement Learning Dan Weld Today s Outline Reinforcement Learning Q-value iteration Q-learning Exploration / exploitation Linear function approximation Many slides
More informationCoarticulation in Markov Decision Processes
Coarticulation in Markov Decision Processes Khashayar Rohanimanesh Department of Computer Science University of Massachusetts Amherst, MA 01003 khash@cs.umass.edu Sridhar Mahadevan Department of Computer
More informationChapter 6 Walk This Way: Spatial Grounding for City Exploration
Chapter 6 Walk This Way: Spatial Grounding for City Exploration Johan Boye, Morgan Fredriksson, Jana Götze, Joakim Gustafson, and Jürgen Königsmann Abstract Recently there has been an interest in spatially
More informationCS 188: Artificial Intelligence Fall Recap: Inference Example
CS 188: Artificial Intelligence Fall 2007 Lecture 19: Decision Diagrams 11/01/2007 Dan Klein UC Berkeley Recap: Inference Example Find P( F=bad) Restrict all factors P() P(F=bad ) P() 0.7 0.3 eather 0.7
More informationSymbolic Dynamic Programming for Continuous State and Observation POMDPs
Symbolic Dynamic Programming for Continuous State and Observation POMDPs Zahra Zamani ANU & NICTA Canberra, Australia zahra.zamani@anu.edu.au Pascal Poupart U. of Waterloo Waterloo, Canada ppoupart@uwaterloo.ca
More informationProbabilistic and Logistic Circuits: A New Synthesis of Logic and Machine Learning
Probabilistic and Logistic Circuits: A New Synthesis of Logic and Machine Learning Guy Van den Broeck KULeuven Symposium Dec 12, 2018 Outline Learning Adding knowledge to deep learning Logistic circuits
More informationArtificial Intelligence
Artificial Intelligence Dynamic Programming Marc Toussaint University of Stuttgart Winter 2018/19 Motivation: So far we focussed on tree search-like solvers for decision problems. There is a second important
More informationCS 343: Artificial Intelligence
CS 343: Artificial Intelligence Hidden Markov Models Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley.
More informationAutomatic Speech Recognition and Statistical Machine Translation under Uncertainty
Outlines Automatic Speech Recognition and Statistical Machine Translation under Uncertainty Lambert Mathias Advisor: Prof. William Byrne Thesis Committee: Prof. Gerard Meyer, Prof. Trac Tran and Prof.
More informationOptimizing Memory-Bounded Controllers for Decentralized POMDPs
Optimizing Memory-Bounded Controllers for Decentralized POMDPs Christopher Amato, Daniel S. Bernstein and Shlomo Zilberstein Department of Computer Science University of Massachusetts Amherst, MA 01003
More informationState Space Compression with Predictive Representations
State Space Compression with Predictive Representations Abdeslam Boularias Laval University Quebec GK 7P4, Canada Masoumeh Izadi McGill University Montreal H3A A3, Canada Brahim Chaib-draa Laval University
More informationPartially Observable Markov Decision Processes (POMDPs) Pieter Abbeel UC Berkeley EECS
Partially Observable Markov Decision Processes (POMDPs) Pieter Abbeel UC Berkeley EECS Many slides adapted from Jur van den Berg Outline POMDPs Separation Principle / Certainty Equivalence Locally Optimal
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Markov Models Instructors: Dan Klein and Pieter Abbeel --- University of California, Berkeley [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to
More informationOptimism in the Face of Uncertainty Should be Refutable
Optimism in the Face of Uncertainty Should be Refutable Ronald ORTNER Montanuniversität Leoben Department Mathematik und Informationstechnolgie Franz-Josef-Strasse 18, 8700 Leoben, Austria, Phone number:
More informationCS188 Outline. CS 188: Artificial Intelligence. Today. Inference in Ghostbusters. Probability. We re done with Part I: Search and Planning!
CS188 Outline We re done with art I: Search and lanning! CS 188: Artificial Intelligence robability art II: robabilistic Reasoning Diagnosis Speech recognition Tracking objects Robot mapping Genetics Error
More informationAutonomous Helicopter Flight via Reinforcement Learning
Autonomous Helicopter Flight via Reinforcement Learning Authors: Andrew Y. Ng, H. Jin Kim, Michael I. Jordan, Shankar Sastry Presenters: Shiv Ballianda, Jerrolyn Hebert, Shuiwang Ji, Kenley Malveaux, Huy
More informationCSC321 Lecture 7 Neural language models
CSC321 Lecture 7 Neural language models Roger Grosse and Nitish Srivastava February 1, 2015 Roger Grosse and Nitish Srivastava CSC321 Lecture 7 Neural language models February 1, 2015 1 / 19 Overview We
More informationProbabilistic Graphical Models for Image Analysis - Lecture 1
Probabilistic Graphical Models for Image Analysis - Lecture 1 Alexey Gronskiy, Stefan Bauer 21 September 2018 Max Planck ETH Center for Learning Systems Overview 1. Motivation - Why Graphical Models 2.
More informationMachine Learning for natural language processing
Machine Learning for natural language processing Classification: Naive Bayes Laura Kallmeyer Heinrich-Heine-Universität Düsseldorf Summer 2016 1 / 20 Introduction Classification = supervised method for
More informationDetection-Based Speech Recognition with Sparse Point Process Models
Detection-Based Speech Recognition with Sparse Point Process Models Aren Jansen Partha Niyogi Human Language Technology Center of Excellence Departments of Computer Science and Statistics ICASSP 2010 Dallas,
More informationOn the Approximate Solution of POMDP and the Near-Optimality of Finite-State Controllers
On the Approximate Solution of POMDP and the Near-Optimality of Finite-State Controllers Huizhen (Janey) Yu (janey@mit.edu) Dimitri Bertsekas (dimitrib@mit.edu) Lab for Information and Decision Systems,
More informationAttention Based Joint Model with Negative Sampling for New Slot Values Recognition. By: Mulan Hou
Attention Based Joint Model with Negative Sampling for New Slot Values Recognition By: Mulan Hou houmulan@bupt.edu.cn CONTE NTS 1 2 3 4 5 6 Introduction Related work Motivation Proposed model Experiments
More informationNovember 28 th, Carlos Guestrin 1. Lower dimensional projections
PCA Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University November 28 th, 2007 1 Lower dimensional projections Rather than picking a subset of the features, we can new features that are
More informationUAPD: Predicting Urban Anomalies from Spatial-Temporal Data
UAPD: Predicting Urban Anomalies from Spatial-Temporal Data Xian Wu, Yuxiao Dong, Chao Huang, Jian Xu, Dong Wang and Nitesh V. Chawla* Department of Computer Science and Engineering University of Notre
More informationPlanning in Markov Decision Processes
Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Planning in Markov Decision Processes Lecture 3, CMU 10703 Katerina Fragkiadaki Markov Decision Process (MDP) A Markov
More informationBayesian Methods for Diagnosing Physiological Conditions of Human Subjects from Multivariate Time Series Biosensor Data
Bayesian Methods for Diagnosing Physiological Conditions of Human Subjects from Multivariate Time Series Biosensor Data Mehmet Kayaalp Lister Hill National Center for Biomedical Communications, U.S. National
More informationProbabilistic Model Checking and Strategy Synthesis for Robot Navigation
Probabilistic Model Checking and Strategy Synthesis for Robot Navigation Dave Parker University of Birmingham (joint work with Bruno Lacerda, Nick Hawes) AIMS CDT, Oxford, May 2015 Overview Probabilistic
More informationBayesian Networks BY: MOHAMAD ALSABBAGH
Bayesian Networks BY: MOHAMAD ALSABBAGH Outlines Introduction Bayes Rule Bayesian Networks (BN) Representation Size of a Bayesian Network Inference via BN BN Learning Dynamic BN Introduction Conditional
More informationA reinforcement learning scheme for a multi-agent card game with Monte Carlo state estimation
A reinforcement learning scheme for a multi-agent card game with Monte Carlo state estimation Hajime Fujita and Shin Ishii, Nara Institute of Science and Technology 8916 5 Takayama, Ikoma, 630 0192 JAPAN
More informationSparse Models for Speech Recognition
Sparse Models for Speech Recognition Weibin Zhang and Pascale Fung Human Language Technology Center Hong Kong University of Science and Technology Outline Introduction to speech recognition Motivations
More informationFinal Exam December 12, 2017
Introduction to Artificial Intelligence CSE 473, Autumn 2017 Dieter Fox Final Exam December 12, 2017 Directions This exam has 7 problems with 111 points shown in the table below, and you have 110 minutes
More informationInformation, Utility & Bounded Rationality
Information, Utility & Bounded Rationality Pedro A. Ortega and Daniel A. Braun Department of Engineering, University of Cambridge Trumpington Street, Cambridge, CB2 PZ, UK {dab54,pao32}@cam.ac.uk Abstract.
More informationCS 5522: Artificial Intelligence II
CS 5522: Artificial Intelligence II Hidden Markov Models Instructor: Wei Xu Ohio State University [These slides were adapted from CS188 Intro to AI at UC Berkeley.] Pacman Sonar (P4) [Demo: Pacman Sonar
More informationA Variance Modeling Framework Based on Variational Autoencoders for Speech Enhancement
A Variance Modeling Framework Based on Variational Autoencoders for Speech Enhancement Simon Leglaive 1 Laurent Girin 1,2 Radu Horaud 1 1: Inria Grenoble Rhône-Alpes 2: Univ. Grenoble Alpes, Grenoble INP,
More informationModeling Norms of Turn-Taking in Multi-Party Conversation
Modeling Norms of Turn-Taking in Multi-Party Conversation Kornel Laskowski Carnegie Mellon University Pittsburgh PA, USA 13 July, 2010 Laskowski ACL 1010, Uppsala, Sweden 1/29 Comparing Written Documents
More informationCausal Belief Decomposition for Planning with Sensing: Completeness Results and Practical Approximation
Causal Belief Decomposition for Planning with Sensing: Completeness Results and Practical Approximation Blai Bonet 1 and Hector Geffner 2 1 Universidad Simón Boĺıvar 2 ICREA & Universitat Pompeu Fabra
More informationState Space Abstractions for Reinforcement Learning
State Space Abstractions for Reinforcement Learning Rowan McAllister and Thang Bui MLG RCC 6 November 24 / 24 Outline Introduction Markov Decision Process Reinforcement Learning State Abstraction 2 Abstraction
More informationBalancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm
Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm Michail G. Lagoudakis Department of Computer Science Duke University Durham, NC 2778 mgl@cs.duke.edu
More information15-381: Artificial Intelligence. Hidden Markov Models (HMMs)
15-381: Artificial Intelligence Hidden Markov Models (HMMs) What s wrong with Bayesian networks Bayesian networks are very useful for modeling joint distributions But they have their limitations: - Cannot
More informationBe able to define the following terms and answer basic questions about them:
CS440/ECE448 Section Q Fall 2017 Final Review Be able to define the following terms and answer basic questions about them: Probability o Random variables, axioms of probability o Joint, marginal, conditional
More information