Q-learning and policy iteration algorithms for stochastic shortest path problems (Q378731): Difference between revisions

@@ Property / Mathematics Subject Classification ID @@
+C40
@@ Property / Mathematics Subject Classification ID: 90C40 / rank @@
+Normal rank
@@ Property / Mathematics Subject Classification ID @@
+C39
@@ Property / Mathematics Subject Classification ID: 90C39 / rank @@
+Normal rank
@@ Property / zbMATH DE Number @@
+6225970
@@ Property / zbMATH DE Number: 6225970 / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+Markov decision processes
@@ Property / zbMATH Keywords: Markov decision processes / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+Q-learning
@@ Property / zbMATH Keywords: Q-learning / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+approximate dynamic programming
@@ Property / zbMATH Keywords: approximate dynamic programming / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+value iteration
@@ Property / zbMATH Keywords: value iteration / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+policy iteration
@@ Property / zbMATH Keywords: policy iteration / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+stochastic shortest paths
@@ Property / zbMATH Keywords: stochastic shortest paths / rank @@
+Normal rank
@@ Property / zbMATH Keywords @@
+stochastic approximation
@@ Property / zbMATH Keywords: stochastic approximation / rank @@
+Normal rank

Revision as of 11:12, 29 June 2023