Travelled to:1 × Australia
1 × Italy
5 × USA
Collaborated with:L.Weaver D.Aberdeen P.L.Bartlett ∅ N.Tao A.Tridgell D.Cosley S.Nomura G.Gay S.Lee B.Alson P.Adams C.Sarabu J.Lewenstein A.Herman J.Holloway K.Boehner
Talks about:gradient (3) social (2) polici (2) museum (2) pomdp (2) learn (2) reinforc (1) programm (1) function (1) approxim (1)
Person: Jonathan Baxter
DBLP: Baxter:Jonathan
Contributed to:
20092008
20022001200019981997Wrote 7 papers:
- CHI-2009-CosleyBLANASG #navigation #semantics #social
- A tag in the hand: supporting semantic, social, and spatial navigation in museums (DC, JB, SL, BA, SN, PA, CS, GG), pp. 1953–1962.
- CHI-2008-CosleyLHHBNBG #named #social
- ArtLinks: fostering social awareness and reflection in museums (DC, JL, AH, JH, JB, SN, KB, GG), pp. 403–412.
- ICML-2002-AberdeenB #scalability
- Scalable Internal-State Policy-Gradient Methods for POMDPs (DA, JB), pp. 3–10.
- ICML-2001-TaoBW #approach #multi #network
- A Multi-Agent Policy-Gradient Approach to Network Routing (NT, JB, LW), pp. 553–560.
- ICML-2000-BaxterB #learning
- Reinforcement Learning in POMDP’s via Direct Gradient Ascent (JB, PLB), pp. 41–48.
- ICML-1998-BaxterTW #named
- KnightCap: A Chess Programm That Learns by Combining TD(λ) with Game-Tree Search (JB, AT, LW), pp. 28–36.
- ICML-1997-Baxter #approximate #canonical
- The Canonical Distortion Measure for Vector Quantization and Function Approximation (JB), pp. 39–47.