An axiomatization of learning rules when counterfactuals are not observed

DOI10.1515/1935-1704.1828MaRDI QIDQ2867503zbMATH OpenOpenAlexFDO

Authors Friederike Mengel, Javier Rivas

Publication date 19 December 2013

Published in The B. E. Journal of Theoretical Economics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1515/1935-1704.1828

zbMATH Keywords

partial informationreinforcement learninglearning without counterfactuals

Mathematics Subject Classification ID

Rationality and learning in game theory (91A26)

Recommendations

• A learning criterion for stochastic rules
• Axioms for rational reinforcement learning
• Probabilistic Rule Learning in Nonmonotonic Domains
• A note on absolutely expedient learning rules
• On the falsifiability and learnability of decision theories
• AI*IA 2005: Advances in Artificial Intelligence
• On the stochastic complexity of learning realizable and unrealizable rules
• Norms and learning in probabilistic logic-based agents
• Learning effect axioms via probabilistic logic programming
• Counterfactual reasoning by (means of) defaults

Cited in

(1)

• Dynamic choice in a complex world

This page was built for publication: An axiomatization of learning rules when counterfactuals are not observed

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2867503)