Travelled to:1 × Finland
1 × France
1 × Israel
1 × Japan
2 × Canada
2 × China
2 × United Kingdom
7 × USA
Collaborated with:R.S.Sutton P.Bachman R.West J.Pineau S.Mannor S.P.Singh Y.Grinberg M.Dinculescu F.Rivest P.E.Utgoff B.Balle P.Panangaden A.M.Farahmand J.Frank P.W.Keller S.Dasgupta A.R.Mahmood H.v.Hasselt D.Azar S.Bouktif B.Kégl H.A.Sahraoui H.R.Maei S.Bhatnagar D.Silver C.Szepesvári E.Wiewiora
Talks about:approxim (7) learn (7) function (4) reinforc (3) tempor (3) polici (3) construct (2) gradient (2) predict (2) partial (2)
Person: Doina Precup
DBLP: Precup:Doina
Contributed to:
2015
2015201420132012
2010201020092009200820062003
20022001200019981997Wrote 19 papers:
- ICML-2015-BachmanP #collaboration #generative #network #probability
- Variational Generative Stochastic Networks with Collaborative Shaping (PB, DP), pp. 1964–1972.
- LICS-2015-BallePP #approximate #automaton #canonical
- A Canonical Form for Weighted Automata and Applications to Approximate Minimization (BB, PP, DP), pp. 701–712.
- ICML-c2-2014-BachmanFP #approximate
- Sample-based approximate regularization (PB, AMF, DP), pp. 1926–1934.
- ICML-c2-2014-SuttonMPH #equivalence #monte carlo
- A new Q(λ) with interim forward view and Monte Carlo equivalence (RSS, ARM, DP, HvH), pp. 568–576.
- ICML-c1-2013-GrinbergP #optimisation
- Average Reward Optimization Objective In Partially Observable Domains (YG, DP), pp. 320–328.
- ICML-2012-PrecupB #estimation #modelling
- Improved Estimation in Time Varying Models (DP, PB), p. 189.
- CIKM-2010-WestPP #automation #documentation #topic
- Automatically suggesting topics for augmenting text documents (RW, DP, JP), pp. 929–938.
- ICML-2010-DinculescuP #approximate #predict
- Approximate Predictive Representations of Partially Observable Systems (MD, DP), pp. 895–902.
- CIKM-2009-WestPP #reduction #wiki
- Completing wikipedia’s hyperlink structure through dimensionality reduction (RW, DP, JP), pp. 1097–1106.
- ICML-2009-SuttonMPBSSW #approximate #learning #linear #performance
- Fast gradient-descent methods for temporal-difference learning with linear function approximation (RSS, HRM, DP, SB, DS, CS, EW), pp. 993–1000.
- ICML-2008-FrankMP #learning
- Reinforcement learning in the presence of rare events (JF, SM, DP), pp. 336–343.
- ICML-2006-KellerMP #approximate #automation #learning #programming
- Automatic basis function construction for approximate dynamic programming and reinforcement learning (PWK, SM, DP), pp. 449–456.
- ICML-2003-RivestP #network
- Combining TD-learning with Cascade-correlation Networks (FR, DP), pp. 632–639.
- ASE-2002-AzarPBKS #adaptation #algorithm #modelling #predict #quality #search-based
- Combining and Adapting Software Quality Predictive Models by Genetic Algorithms (DA, DP, SB, BK, HAS), pp. 285–288.
- ICML-2001-PrecupSD #approximate #difference #learning
- Off-Policy Temporal Difference Learning with Function Approximation (DP, RSS, SD), pp. 417–424.
- ICML-2000-PrecupSS #evaluation #policy
- Eligibility Traces for Off-Policy Policy Evaluation (DP, RSS, SPS), pp. 759–766.
- ICML-1998-PrecupU #approximate #classification #using
- Classification Using Phi-Machines and Constructive Function Approximation (DP, PEU), pp. 439–444.
- ICML-1998-SuttonPS #learning
- Intra-Option Learning about Temporally Abstract Actions (RSS, DP, SPS), pp. 556–564.
- ICML-1997-PrecupS #learning
- Exponentiated Gradient Methods for Reinforcement Learning (DP, RSS), pp. 272–277.