Title of article
Average cost temporal-difference learning
Author/Authors
John N. Tsitsiklis، نويسنده , , Benjamin Van Roy، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 1999
Pages
10
From page
1799
To page
1808
Keywords
Dynamic programming , learning , Average cost , reinforcement learning , Neuro-dynamic programming , approximation , Temporaldi!erences
Journal title
Automatica
Serial Year
1999
Journal title
Automatica
Record number
368887
Link To Document