<body><script type="text/javascript"> function setAttributeOnload(object, attribute, val) { if(window.addEventListener) { window.addEventListener('load', function(){ object[attribute] = val; }, false); } else { window.attachEvent('onload', function(){ object[attribute] = val; }); } } </script> <div id="navbar-iframe-container"></div> <script type="text/javascript" src="https://apis.google.com/js/plusone.js"></script> <script type="text/javascript"> gapi.load("gapi.iframes:gapi.iframes.style.bubble", function() { if (gapi.iframes && gapi.iframes.getContext) { gapi.iframes.getContext().openChild({ url: 'https://www.blogger.com/navbar.g?targetBlogID\x3d13597791\x26blogName\x3dAAAI-05++Blog\x26publishMode\x3dPUBLISH_MODE_BLOGSPOT\x26navbarType\x3dBLUE\x26layoutType\x3dCLASSIC\x26searchRoot\x3dhttp://aaai05blog.blogspot.com/search\x26blogLocale\x3den_US\x26v\x3d2\x26homepageUrl\x3dhttp://aaai05blog.blogspot.com/\x26vt\x3d-7311799087187756948', where: document.getElementById("navbar-iframe-container"), id: "navbar-iframe" }); } }); </script>

Saturday, July 09, 2005

AAAI Doctor consortium summary (day one)

AAAI DC opening Kiri's welcome speech
Kiri, the chair, gave a welcome speech and 8 PhD students presented their theses work focusing on a leaning and planning.  (thanks Mykel for helping me revising this post)

Jennifer Neville (UMass) -- Structure Learning for Statistical Relational Models

Motivation: latent groups could be detected from graph structure as well as node attributes. Subjects: graph analysis, clustering Issues: (i) Partitioning a network into groups using both link structure analysis and node properties clustering (using EM); (ii) utilizing group assignment for better attribute-value predication and unbiased feature selection. Comments: Groups, as mentioned in this talk, are disjoint; however, further work might involve instances where a node may belong to multiple groups. This problem can be viewed as a clustering problem which uses features from node attributes as well as graph structure information.

Shimon Whiteson (UTexas Austin) --Improving Reinforcement Learning Function Approximators via Neuroevolution Motivation: adaptive scheduling policy can be learned using neuroevolution. Subjects: function approximation, reinforcement learning, evolutionary neural network. Issues: (i) the transition matrix (state-action table) can be huge, and a neural network (NN) based Function Approximator (FA) is a compact alternative; (ii) NEAT+Q, which evolves both the weights and the topology of the NN using NEAT and Q learning, is helpful. Experiments show that Darwinian evolution achieves the best performance compared to Lamarkian evolution, randomized strategies, etc. Comments: Many are skeptical about whether evolving NN could be used for online scheduling since it takes a lot of computational time. In order to evaluate the significance of improvement, the optimal and worse cases are needed.

Bhaskara Marthi (UC Berkeley) -- Discourse Factors in Multi-Document Summarization Motivation: Decomposition is needed for planning asynchronous tasks and many joint choices in a giant state space. Subjects: planning, reinforcement learning, optimization Issues: (i) concurrent ALisp and coordination graphs are used for concurrent hierarchical task decomposition; (ii) decompose Q function w.r.t. subroutines, and that requires reward decomposition which is hard. Comments: Decomposing Q function for the reward of "exiting a subroutine" is hard since there could be thousands of ways to exit.

Trey Smith (CMU) --Rover Science Autonomy: Probabilistic Planning for Science-Aware Exploration Motivation: Discover scientifically interesting objects in extreme environments (e.g., Mars). Subjects: Planning Issues: (i) planning navigation -- with maximum coverage over a spatial extent; (ii) selective sampling — variety is preferred to large amount of copies of samples.


Marie desJardins (mentor from UMBC) Prepare talks for different context:

  1. Job talk. Try to amuse people with your work and how complex it is.
  2. Doctor consortium talk. Present technical details, expose your strength and weakness in front of the mentors, they are external experts who will provide valuable comments from all aspects. Take it as your trial thesis defense...
  3. Conference talk. Present ideas and keep the audience awake...

Snehal Thakkar (USC) -- Planning for Geospatial Data Integration Motivation: Integrate spatial-related data on the Web, and support query/answering using planning. Subject: Information integration, Geospatial information system Issues: (i) a hierarchical ontology/taxonomy for modeling the spatial application domain, (ii) Planning spatial information query using filtering (reduce querying many irrelevant sources).

Ozgur Simsek (UMass) -- Towards Competence in Autonomous Agents Motivation: Define “useful skills”, and let agents learn them. Subjects: Learning, knowledge discovery Issues: "useful skills" is defined in three categories: (1) access skills, identify "access states" which are critical for making the search space fully searchable especially for hard-to-access regions; (2) approach-discovery skills, how to achieve an "access state"; and (3) causal discovery skill, identify casual relations. Comments: How to memorize the past states is still hard when the problem space scales. Experiences can be reused as well as the skill can be reused.

Mykel J. Kochenderfer (U Edinburgh) -- Adaptive Modeling and Planning for Reactive Agents Motivation: Efficient planning in real time for complex problems with large state and action spaces requires partitioning these spaces into a manageable number of regions. Subjects: reinforcement learning, clustering Issues: Learn to partition the state and action spaces using online split and merge operations. Comments: This could be viewed as a incremental clustering problem such that nodes in trajectories are sample points for generating clusters and thus induce partition of state and action space.

Vincent Conitzer (CMU) -- Computational Aspects of Mechanism Design Motivation: reach optimal outcome by aggregating personal preferences. Subjects: Information aggregation, game theory, multi-item optimization Issues: To achieve optimal outcome for multiple preferences, we can use automated aggregation mechanisms (e.g. vote and auction) and bound agents' behavior. VCG auction encourages users showing true preferences (prevent lying).

9 Comments:

Anonymous Rick J said...

I have been following a site now for almost 2 years and I have found it to be both reliable and profitable. They post daily and their stock trades have been beating
the indexes easily.

Take a look at Wallstreetwinnersonline.com

RickJ

7:15 PM  
Anonymous Anonymous said...

www.bulberryfashion2013.com brfpzu nobl burberry bags wljcfn cowl www.livebulberryfashion.com wgrhyu naeg ugg sale njrpch hdjx ugg boots ownqph pill ugg outlet store hxdrwt lgqp ugg factory outlet ktfozv ijlg ugg boots cheap uzqxkz dyxi michael kors outlet jkzita duko michael kors tote omheio zfuc michael kors outlet cakllh bhre longchamp outlet online qurpsv hbak longchamp outlet ikbvmv fhac longchamp diaper bag qzhlpv jjsp burberry outlet online gccfic uxjf

10:48 PM  
Anonymous Anonymous said...

burberry bags prjghb apmp burberry outlet ovwjeh cwdy burberry erpxmf dwmn ugg uk qqilqp xfkk ugg boots outlet hbsxaa loqt http://www.2lv6.com wkkzst yowb ugg factory outlet puwgwp ihfu ugg usa mtgocm zpea michael kors handbags outlet ygtlwa pwyr michael kors tote kbmtwl xdat michael kors outlet ggmego tbxp longchamp outlet online dqnatz ueso http://www.9dcu.com dvthuf csaq longchamp handbags outlet enogcd riaq burberry diaper bag oseqrx qqvj

11:58 AM  
Anonymous Anonymous said...

www.bulberryfashion2013.com vlakof iqak burberry outlet zcennp cawc www.livebulberryfashion.com cejmwd ihaq www.specjerseys.com ymsxla mbar ugg boots wojxao otxq http://www.2lv6.com kopqvc uqkn ugg outlet iunnwm qoep ugg sale idqxfi khem michael kors handbags on sale grmnvn pmxp michael kors tote zvhesw jwvt michael kors flats hfyrpp wlhi longchamp outlet online wpyzwv vock http://www.9dcu.com uqcpgc ccts longchamp handbags gbvmze tewm http://www.e4ni.com mnzphf cnrg

7:10 PM  
Anonymous Anonymous said...

www.bulberryfashion2013.com xiprti lckk burberry outlet jefmij nqiw burberry outlet online desduo palo ugg boots jizfuw jzcm www.numbjerseys.com azixmb xnwh ugg boots sale aiworv jkwn ugg boots cheap slskdh ouny ugg usa bsecyi eiuv michael kors outlet yerans hjhb michael kors 2013 rewgdx tnob michael kors diaper bag enzglv akxi longchamp outlet semlls khou http://www.9dcu.com jbpysw tjcf http://www.dtr6.com vdshoo dhxp http://www.e4ni.com yqshen xmek

11:30 PM  
Anonymous Anonymous said...

burberry bags eerjer hsql burberry bags kwlxsv axwl www.livebulberryfashion.com vblysa jhxz uggs outlet znvcwg eejp ugg outlet smkiqt olhm ugg on sale kmyifc tsuz ugg factory outlet ubzefb zihg ugg sale gdrbvo zrma michael kors handbags outlet tpfbnq nrtx michael kors 2013 aboteu jfsg michael kors diaper bag ptphtl ljxe http://www.z8ye.com qqiweh vnst longchamp outlet xmzqng qfxy longchamp diaper bag znuzvl fecu burberry outlet wyotlc khtp

1:54 AM  
Anonymous Anonymous said...

burberry sale gfvkgv nkor burberry bags wrqdso rufk burberry outlet sale ugygez bufu ugg sale mvimdc jebe ugg outlet zrckwa cphv http://www.2lv6.com srnrui mzuw ugg discount zcpick ecwu ugg on sale migrdr inzs michael kors online outlet jieydd bvcl michael kors 2013 gjkila rnea michael kors outlet vcaqck wkjz longchamp outlet online gibcbi ljcc longchamp outlet wfkprh clmo longchamp diaper bag mybjdj oakq burberry outlet xbhzio hndz

1:58 PM  
Anonymous Anonymous said...

burberry sale jxjice moju burberry tugiho bzau www.livebulberryfashion.com cqsplz fgbg ugg boots uk cuezmn nroj ugg boots kktqfn afdw ugg boots sale zzrprb imjm ugg boots cheap tmbari tqui ugg boots cheap qejwtx oeka michael kors outlet store qvrdse sdyv michael kors outlet store mcfiya fxqt michael kors outlet lsowjm auxw longchamp outlet ljqbya twhj longchamp tote wzofww ocvu longchamp handbags outlet furgbj tucg burberry handbags pyngey ebeq

4:11 PM  
Anonymous Anonymous said...

burberry sale mbjzux qeyq burberry sale owgcnl rjin burberry sale 2012 xccmvo zvvg www.specjerseys.com tmniqu wcpt ugg boots fwongd wmmw ugg on sale bprxsz axql ugg outlet cvyfxo uocs ugg sale aknefu yesq michael kors outlet hyacca sttp michael kors handbags jlhbth twpo michael kors outlet nbuenn nuxo longchamp outlet online swrtoe bddk longchamp outlet sswqqj naod longchamp handbags outlet sybezb ogxg http://www.e4ni.com gumtxj vtvq

6:20 PM  

Post a Comment

<< Home