iRobotLab

• 追加された行はこの色です。
• 削除された行はこの色です。
• 研究/ResearchActivity/2011-001 へ行く。
• 研究/ResearchActivity/2011-001 の差分を削除

[[研究/各研究の話]]
*Efficient learning by making a choice of sensor information [#qa80d2b9]
**Summary [#n58aacdf]
-Focusing of a relationships between sensor information and degrees of achievement of task.
-Calculating coefficient of correlation between sensor value and reward on reinforcement learning as degrees of achievement of task.
-Agent select important sensors for task based on coefficient of correlation.
-Agent reduces Q-space which is used important sensors only.

**Conceptual diagram [#n9ad6938]
#ref(The_way_of_decide_important_sensors.png,center,45%)

#ref(Reduction_of_sensor_space.png,center,40%)