On tight bounds for function approximation error in risk-sensitive reinforcement learning (Q2243003): Difference between revisions

@@ Property / cites work @@
+Risk-averse dynamic programming for Markov decision processes
+Normal rank
@@ Property / cites work @@
+Markov decision processes with average-value-at-risk criteria
+Normal rank
@@ Property / cites work @@
+Q5201296
@@ Property / cites work: Q5201296 / rank @@
+Normal rank
@@ Property / cites work @@
+A quantitative comparison of risk measures
@@ Property / cites work: A quantitative comparison of risk measures / rank @@
+Normal rank
@@ Property / cites work @@
+Multiplicative ergodicity and large deviations for an irreducible Markov chain.
+Normal rank
@@ Property / cites work @@
+Risk-Sensitive Optimal Control for Markov Decision Processes with Monotone Cost
+Normal rank
@@ Property / cites work @@
+Stochastic approximation with `controlled Markov' noise
+Normal rank
@@ Property / cites work @@
+Simulation-based optimization of Markov reward processes
+Normal rank
@@ Property / cites work @@
+Q-Learning for Risk-Sensitive Control
@@ Property / cites work: Q-Learning for Risk-Sensitive Control / rank @@
+Normal rank
@@ Property / cites work @@
+A sensitivity formula for risk-sensitive cost and the actor-critic algorithm
+Normal rank
@@ Property / cites work @@
+Comparing the Spectral Radii of Two Nonnegative Matrices
+Normal rank
@@ Property / cites work @@
+On comparison of the Perron-Frobenius eigenvalues of two ML-matrices
+Normal rank
@@ Property / cites work @@
+Inequalities
@@ Property / cites work: Inequalities / rank @@
+Normal rank
@@ Property / cites work @@
+On the Maximal Eigenvector of a Positive Matrix
@@ Property / cites work: On the Maximal Eigenvector of a Positive Matrix / rank @@
+Normal rank