`Travelled to:`

1 × China

1 × Finland

2 × Canada

4 × USA

`Collaborated with:`

M.L.Littman J.Langford E.Brunskill ∅ R.Parr C.Painter-Wakefield W.Chu M.Dudík C.Diuk B.R.Leffler T.J.Walsh M.Zinkevich A.Thomas B.L.Tseng G.Taylor A.L.Strehl E.Wiewiora A.Agarwal D.Hsu S.Kale R.E.Schapire T.Moon C.Liao Z.Zheng Y.Chang

`Talks about:`

learn (9) reinforc (4) function (3) approxim (3) linear (3) featur (3) select (2) onlin (2) model (2) valu (2)

## Person: Lihong Li

### DBLP: Li:Lihong

### Contributed to:

### Wrote 11 papers:

- ICML-c2-2014-AgarwalHKLLS #algorithm #performance
- Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits (AA, DH, SK, JL, LL, RES), pp. 1638–1646.
- ICML-c2-2014-BrunskillL #learning
- PAC-inspired Option Discovery in Lifelong Reinforcement Learning (EB, LL), pp. 316–324.
- ICML-2011-DudikLL #evaluation #learning #policy #robust
- Doubly Robust Policy Evaluation and Learning (MD, JL, LL), pp. 1097–1104.
- KDD-2011-ChuZLTT #data type #learning #online
- Unbiased online active learning in data streams (WC, MZ, LL, AT, BLT), pp. 195–203.
- CIKM-2010-MoonLCLZC #feedback #learning #online #ranking #realtime #using
- Online learning for recency search ranking using real-time user feedback (TM, LL, WC, CL, ZZ, YC), pp. 1501–1504.
- ICML-2009-DiukLL #adaptation #feature model #learning #problem
- The adaptive k-meteorologists problem and its application to structure learning and feature selection in reinforcement learning (CD, LL, BRL), pp. 249–256.
- ICML-2008-Li #approximate #comparison #difference #linear #worst-case
- A worst-case comparison between temporal difference and residual gradient with linear function approximation (LL), pp. 560–567.
- ICML-2008-LiLW #framework #learning #self #what
- Knows what it knows: a framework for self-aware learning (LL, MLL, TJW), pp. 568–575.
- ICML-2008-ParrLTPL #analysis #approximate #feature model #learning #linear #modelling
- An analysis of linear models, linear value-function approximation, and feature selection for reinforcement learning (RP, LL, GT, CPW, MLL), pp. 752–759.
- ICML-2007-ParrPLL #approximate #generative
- Analyzing feature generation for value-function approximation (RP, CPW, LL, MLL), pp. 737–744.
- ICML-2006-StrehlLWLL #learning
- PAC model-free reinforcement learning (ALS, LL, EW, JL, MLL), pp. 881–888.