研究/ResearchActivity/2012年度/01 の変更点


[[研究/各研究の話/2012年度]]
*強化学習におけるセンサの重要度に応じた効率的な意思決定(Efficiently Decision making in reinforcement learning based on importance of sensor) [#yab451db]

**Summary [#n58aacdf]
-Focusing of a relationships between sensor value and reward as a barometer of importance of sensors.
-Calculatiing multiple regression coefficient between imput values of sensors and reward as degree ofimportance of sensors.
-To selecto action, temporary Q-space is constructed from original Q-space baced on degree of importance of sensors.
-Focusing on a relationships between sensor value and reward as a barometer of importance of sensors.
-Calculating multiple regression coefficient between imput values of sensors and reward as degree of importance of sensors.
-To select an action, temporary Q-space is constructed from original Q-space based on degree of importance of sensors.
-Higher degree of importance of sensors, more the number of state of temporary Q-space.

**Conceptual diagram [#n9ad6938]
#ref(research_activity_1.png,center,30%)

#ref(research_activity_2.png,center,30%)

#ref(research_activity_3.png,center,40%)