Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386317039> ?p ?o ?g. }
- W4386317039 endingPage "158" @default.
- W4386317039 startingPage "125" @default.
- W4386317039 abstract "The development process for reinforcement learning applications is still exploratory rather than systematic. This exploratory nature reduces reuse of specifications between applications and increases the chances of introducing programming errors. This paper takes a step towards systematizing the development of reinforcement learning applications. We introduce a formal specification of reinforcement learning problems and algorithms, with a particular focus on temporal difference methods and their definitions in backup diagrams. We further develop a test harness for a large class of reinforcement learning applications based on temporal difference learning, including SARSA and Q-learning. The entire development is rooted in functional programming methods; starting with pure specifications and denotational semantics, ending with property-based testing and using compositional interpreters for a domain-specific term language as a test oracle for concrete implementations. We demonstrate the usefulness of this testing method on a number of examples, and evaluate with mutation testing. We show that our test suite is effective in killing mutants (90% mutants killed for 75% of subject agents). More importantly, almost half of all mutants are killed by generic write-once-use-everywhere tests that apply to any reinforcement learning problem modeled using our library, without any additional effort from the programmer." @default.
- W4386317039 created "2023-09-01" @default.
- W4386317039 creator A5036805687 @default.
- W4386317039 creator A5039414480 @default.
- W4386317039 creator A5056755949 @default.
- W4386317039 creator A5088284921 @default.
- W4386317039 date "2023-08-30" @default.
- W4386317039 modified "2023-09-27" @default.
- W4386317039 title "Formal Specification and Testing for Reinforcement Learning" @default.
- W4386317039 cites W2026926213 @default.
- W4386317039 cites W2049695835 @default.
- W4386317039 cites W2050509196 @default.
- W4386317039 cites W2100677568 @default.
- W4386317039 cites W2100752967 @default.
- W4386317039 cites W2107726111 @default.
- W4386317039 cites W2108557864 @default.
- W4386317039 cites W2222789563 @default.
- W4386317039 cites W2593237273 @default.
- W4386317039 cites W2725449579 @default.
- W4386317039 cites W2787908307 @default.
- W4386317039 cites W2869036160 @default.
- W4386317039 cites W2941205169 @default.
- W4386317039 cites W2963575966 @default.
- W4386317039 cites W2963913218 @default.
- W4386317039 cites W3003931103 @default.
- W4386317039 cites W3021958118 @default.
- W4386317039 cites W3102039646 @default.
- W4386317039 cites W3104303413 @default.
- W4386317039 cites W3122478777 @default.
- W4386317039 cites W3163745263 @default.
- W4386317039 cites W3179011554 @default.
- W4386317039 cites W3193448347 @default.
- W4386317039 cites W3198594207 @default.
- W4386317039 cites W3200467243 @default.
- W4386317039 cites W3206959716 @default.
- W4386317039 cites W3208792968 @default.
- W4386317039 cites W3217518341 @default.
- W4386317039 cites W4206624744 @default.
- W4386317039 cites W4225756091 @default.
- W4386317039 cites W4232976691 @default.
- W4386317039 cites W4242126179 @default.
- W4386317039 cites W4282580266 @default.
- W4386317039 cites W4284682097 @default.
- W4386317039 cites W4285601900 @default.
- W4386317039 cites W4289874473 @default.
- W4386317039 cites W4312510909 @default.
- W4386317039 cites W4313547546 @default.
- W4386317039 cites W4313563646 @default.
- W4386317039 cites W4367016230 @default.
- W4386317039 doi "https://doi.org/10.1145/3607835" @default.
- W4386317039 hasPublicationYear "2023" @default.
- W4386317039 type Work @default.
- W4386317039 citedByCount "0" @default.
- W4386317039 crossrefType "journal-article" @default.
- W4386317039 hasAuthorship W4386317039A5036805687 @default.
- W4386317039 hasAuthorship W4386317039A5039414480 @default.
- W4386317039 hasAuthorship W4386317039A5056755949 @default.
- W4386317039 hasAuthorship W4386317039A5088284921 @default.
- W4386317039 hasBestOaLocation W43863170391 @default.
- W4386317039 hasConcept C115903868 @default.
- W4386317039 hasConcept C119857082 @default.
- W4386317039 hasConcept C128942645 @default.
- W4386317039 hasConcept C151552104 @default.
- W4386317039 hasConcept C152877465 @default.
- W4386317039 hasConcept C154945302 @default.
- W4386317039 hasConcept C199360897 @default.
- W4386317039 hasConcept C2778514511 @default.
- W4386317039 hasConcept C41008148 @default.
- W4386317039 hasConcept C55166926 @default.
- W4386317039 hasConcept C77967617 @default.
- W4386317039 hasConcept C97541855 @default.
- W4386317039 hasConceptScore W4386317039C115903868 @default.
- W4386317039 hasConceptScore W4386317039C119857082 @default.
- W4386317039 hasConceptScore W4386317039C128942645 @default.
- W4386317039 hasConceptScore W4386317039C151552104 @default.
- W4386317039 hasConceptScore W4386317039C152877465 @default.
- W4386317039 hasConceptScore W4386317039C154945302 @default.
- W4386317039 hasConceptScore W4386317039C199360897 @default.
- W4386317039 hasConceptScore W4386317039C2778514511 @default.
- W4386317039 hasConceptScore W4386317039C41008148 @default.
- W4386317039 hasConceptScore W4386317039C55166926 @default.
- W4386317039 hasConceptScore W4386317039C77967617 @default.
- W4386317039 hasConceptScore W4386317039C97541855 @default.
- W4386317039 hasIssue "ICFP" @default.
- W4386317039 hasLocation W43863170391 @default.
- W4386317039 hasOpenAccess W4386317039 @default.
- W4386317039 hasPrimaryLocation W43863170391 @default.
- W4386317039 hasRelatedWork W1503760549 @default.
- W4386317039 hasRelatedWork W2597787948 @default.
- W4386317039 hasRelatedWork W3025582806 @default.
- W4386317039 hasRelatedWork W3137189469 @default.
- W4386317039 hasRelatedWork W3160136729 @default.
- W4386317039 hasRelatedWork W4206956498 @default.
- W4386317039 hasRelatedWork W4237428255 @default.
- W4386317039 hasRelatedWork W4246531319 @default.
- W4386317039 hasRelatedWork W4319083788 @default.
- W4386317039 hasRelatedWork W1482645738 @default.
- W4386317039 hasVolume "7" @default.