| 2008 |
|---|
| 14 | EE | Harukazu Igarashi,
K. Nakamura,
Seiji Ishihara:
Learning of soccer player agents using a policy gradient method: Coordination between kicker and receiver during free kicks.
IJCNN 2008: 46-52 |
| 13 | EE | Seiji Ishihara,
Harukazu Igarashi:
Behavior Learning Based on a Policy Gradient Method: Separation of Environmental Dynamics and State Values in Policies.
PRICAI 2008: 164-174 |
| 2006 |
|---|
| 12 | EE | Seiji Ishihara,
Harukazu Igarashi:
A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems.
HIS 2006: 28 |
| 11 | EE | Seiji Ishihara,
Harukazu Igarashi:
Applying the policy gradient method to behavior learning in multiagent systems: The pursuit problem.
Systems and Computers in Japan 37(10): 101-109 (2006) |
| 2005 |
|---|
| 10 | EE | Seiji Ishihara,
Harukazu Igarashi:
A Task Decomposition Algorithm Using Radial Basis Functions for Classification Problems.
DICTA 2005: 2 |
| 2003 |
|---|
| 9 | | Seiji Ishihara,
Harukazu Igarashi:
Policy Gradient Methods in Multi-Agent Systems.
HIS 2003: 789-798 |
| 8 | EE | Harukazu Igarashi,
Kiyoshi Ioi:
Navigation of a mobile robot formulated in terms of discrete optimization problems.
Systems and Computers in Japan 34(6): 59-68 (2003) |
| 2002 |
|---|
| 7 | EE | Kiyoshi Ioi,
Harukazu Igarashi,
Ayanobu Murakami:
Design of a gravitational wheeled robot.
Advanced Robotics 16(8): 785-793 (2002) |
| 2000 |
|---|
| 6 | EE | Harukazu Igarashi:
Path Planning of a Mobile Robot as a Discrete Optimization Problem an Adjustment of Weight Parameters in the Objective Function by Reinforcement Learning.
RoboCup 2000: 315-320 |
| 5 | EE | Harukazu Igarashi,
Yusuke Yamauchi,
Shuichi Iidoi:
RoboCup 2000 Simulation League: Team KU-Yam2000.
RoboCup 2000: 445-448 |
| 1999 |
|---|
| 4 | | Harukazu Igarashi,
Shougo Kosue,
Takashi Sakurai:
RoboCup-99 Simulation League: Team KU-Sakura2.
RoboCup 1999: 596-599 |
| 1998 |
|---|
| 3 | EE | Harukazu Igarashi,
Shougo Kosue,
Masatoshi Miyahara:
Individual Tactical Play and Pass with Communication between Players - Team descriptions of Team Miya2.
RoboCup 1998: 364-370 |
| 1997 |
|---|
| 2 | | Harukazu Igarashi,
Shougo Kosue,
Masatoshi Miyahara,
Toshiro Umaba:
Individual Tactical Play and Action Decision Based on a Short-Term Goal - Team Descriptions of Team Miya and Team Niken.
RoboCup 1997: 420-427 |
| 1 | EE | Hideo Itoyama,
Harukazu Igarashi,
Hironao Kawashima:
Adjustment of term weights in an energy function used in the simulated annealing approach to vehicle scheduling problems.
Systems and Computers in Japan 28(2): 1-10 (1997) |
