US2006190156A1PendingUtilityA1

Learning control apparatus, learning control method, and computer program

Assignee: SONY CORPPriority: Feb 23, 2005Filed: Feb 6, 2006Published: Aug 24, 2006
Est. expiryFeb 23, 2025(expired)· nominal 20-yr term from priority
G05B 13/0265
48
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, includes an estimating unit for estimating a causal relationship of at least one variable, a grouping unit for grouping at least one variable into a variable group in accordance with the estimated causal relationship, a determining for determining a behavior variable corresponding to each of the variable groups, and a layering unit for layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.

Claims

exact text as granted — not AI-modified
1 . A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, the learning control apparatus comprising: 
 estimating means for estimating a causal relationship of at least one variable;    grouping means for grouping the at least one variable into a variable group in accordance with the estimated causal relationship;    first determining means for determining a behavior variable corresponding to each of the variable groups; and    layering means for layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.    
   
   
       2 . The learning control apparatus according to  claim 1 , further comprising second determining means for determining a state variable corresponding to each variable group.  
   
   
       3 . A learning control method for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, the learning control method comprising steps of: 
 estimating a causal relationship of at least one variable;    grouping the at least one variable into a variable group in accordance with the estimated causal relationship;    determining a behavior variable corresponding to each of the variable groups; and    layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.    
   
   
       4 . A computer program for causing a computer to control learning of an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, the computer program comprising steps of: 
 estimating a causal relationship of at least one variable;    grouping the at least one variable into a variable group in accordance with the estimated causal relationship;    determining a behavior variable corresponding to each of the variable groups; and    layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.    
   
   
       5 . A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, the learning control apparatus comprising: 
 an estimating unit estimating a causal relationship of at least one variable;    a grouping unit grouping the at least one variable into a variable group in accordance with the estimated causal relationship;    a determining unit determining a behavior variable corresponding to each of the variable groups; and    a layering unit layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable.

Join the waitlist — get patent alerts

Track US2006190156A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.