Travelled to:1 × Finland
1 × Slovenia
6 × USA
Collaborated with:H.Kimura J.Sakuma M.Sato R.N.Wright S.Katayama K.Miyazaki M.Yamamura
Talks about:learn (7) reinforc (5) function (3) control (2) analysi (2) reward (2) linear (2) use (2) imperfect (1) algorithm (1)
Person: Shigenobu Kobayashi
DBLP: Kobayashi:Shigenobu
Contributed to:
2009
2008200120001999199819971995Wrote 8 papers:
- SIGIR-2009-SakumaK #analysis #graph
- Link analysis for private weighted graphs (JS, SK), pp. 235–242.
- ICML-2008-SakumaKW #learning #privacy
- Privacy-preserving reinforcement learning (JS, SK, RNW), pp. 864–871.
- ICML-2001-SatoK #learning #markov #problem
- Average-Reward Reinforcement Learning for Variance Penalized Markov Decision Problems (MS, SK), pp. 473–480.
- ICML-2000-KatayamaKK #learning #using
- A Universal Generalization for Temporal-Difference Learning Using Haar Basis Functions (SK, HK, SK), pp. 447–454.
- ICML-1999-KimuraK #linear #performance
- Efficient Non-Linear Control by Combining Q-learning with Local Linear Controllers (HK, SK), pp. 210–219.
- ICML-1998-KimuraK #algorithm #analysis #learning #using
- An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function (HK, SK), pp. 278–286.
- ICML-1997-KimuraMK #approximate #learning
- Reinforcement Learning in POMDPs with Function Approximation (HK, KM, SK), pp. 152–160.
- ICML-1995-KimuraYK #learning #probability
- Reinforcement Learning by Stochastic Hill Climbing on Discounted Reward (HK, MY, SK), pp. 295–303.