Guiding exploration by pre-existing knowledge without modifying reward (Q2383522): Difference between revisions

@@ Property / describes a project that uses @@
+R-MAX
@@ Property / describes a project that uses: R-MAX / rank @@
+Normal rank
@@ Property / MaRDI profile type @@
+MaRDI publication profile
@@ Property / MaRDI profile type: MaRDI publication profile / rank @@
+Normal rank
@@ Property / Wikidata QID @@
+Q48409246
@@ Property / Wikidata QID: Q48409246 / rank @@
+Normal rank
@@ Property / full work available at URL @@
+https://doi.org/10.1016/j.neunet.2007.02.001
+Normal rank
@@ Property / OpenAlex ID @@
+W2065727890
@@ Property / OpenAlex ID: W2065727890 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4257216
@@ Property / cites work: Q4257216 / rank @@
+Normal rank
@@ Property / cites work @@
+.1162/153244303765208377
@@ Property / cites work: 10.1162/153244303765208377 / rank @@
+Normal rank
@@ Property / cites work @@
+Continuous-action Q-learning
@@ Property / cites work: Continuous-action Q-learning / rank @@
+Normal rank
@@ Property / cites work @@
+Reinforcement learning with replacing eligibility traces
+Normal rank
@@ Property / cites work @@
+Convergence results for single-step on-policy reinforcement-learning algorithms
+Normal rank