Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211270166> ?p ?o ?g. }
- W3211270166 abstract "Contemporary coding education often presents students with the task of developing programs that have user interaction and complex dynamic systems, such as mouse based games. While pedagogically compelling, there are no contemporary autonomous methods for providing feedback. Notably, interactive programs are impossible to grade by traditional unit tests. In this paper we formalize the challenge of providing feedback to interactive programs as a task of classifying Markov Decision Processes (MDPs). Each student's program fully specifies an MDP where the agent needs to operate and decide, under reasonable generalization, if the dynamics and reward model of the input MDP should be categorized as correct or broken. We demonstrate that by designing a cooperative objective between an agent and an autoregressive model, we can use the agent to sample differential trajectories from the input MDP that allows a classifier to determine membership: Play to Grade. Our method enables an automatic feedback system for interactive code assignments. We release a dataset of 711,274 anonymized student submissions to a single assignment with hand-coded bug labels to support future research." @default.
- W3211270166 created "2021-11-08" @default.
- W3211270166 creator A5018535992 @default.
- W3211270166 creator A5074969309 @default.
- W3211270166 creator A5084989076 @default.
- W3211270166 date "2021-10-27" @default.
- W3211270166 modified "2023-09-26" @default.
- W3211270166 title "Play to Grade: Testing Coding Games as Classifying Markov Decision Process" @default.
- W3211270166 cites W1533853869 @default.
- W3211270166 cites W2004921952 @default.
- W3211270166 cites W2042742211 @default.
- W3211270166 cites W2058735307 @default.
- W3211270166 cites W2064675550 @default.
- W3211270166 cites W2107726111 @default.
- W3211270166 cites W2129740354 @default.
- W3211270166 cites W2170296074 @default.
- W3211270166 cites W2181068523 @default.
- W3211270166 cites W2183293350 @default.
- W3211270166 cites W2246775628 @default.
- W3211270166 cites W2308618763 @default.
- W3211270166 cites W2397240726 @default.
- W3211270166 cites W2568646110 @default.
- W3211270166 cites W2736629007 @default.
- W3211270166 cites W2748832454 @default.
- W3211270166 cites W2751973545 @default.
- W3211270166 cites W2771764532 @default.
- W3211270166 cites W2805937758 @default.
- W3211270166 cites W2903075639 @default.
- W3211270166 cites W2913657017 @default.
- W3211270166 cites W2914261249 @default.
- W3211270166 cites W2915075219 @default.
- W3211270166 cites W2923223302 @default.
- W3211270166 cites W2951004968 @default.
- W3211270166 cites W2952109936 @default.
- W3211270166 cites W2953091398 @default.
- W3211270166 cites W2953318193 @default.
- W3211270166 cites W2963438456 @default.
- W3211270166 cites W2963666583 @default.
- W3211270166 cites W3000499753 @default.
- W3211270166 cites W3008165446 @default.
- W3211270166 cites W3035644784 @default.
- W3211270166 cites W3046946156 @default.
- W3211270166 cites W3136629921 @default.
- W3211270166 cites W3137081879 @default.
- W3211270166 cites W3146075203 @default.
- W3211270166 cites W650350307 @default.
- W3211270166 doi "https://doi.org/10.48550/arxiv.2110.14615" @default.
- W3211270166 hasPublicationYear "2021" @default.
- W3211270166 type Work @default.
- W3211270166 sameAs 3211270166 @default.
- W3211270166 citedByCount "0" @default.
- W3211270166 crossrefType "posted-content" @default.
- W3211270166 hasAuthorship W3211270166A5018535992 @default.
- W3211270166 hasAuthorship W3211270166A5074969309 @default.
- W3211270166 hasAuthorship W3211270166A5084989076 @default.
- W3211270166 hasBestOaLocation W32112701661 @default.
- W3211270166 hasConcept C105795698 @default.
- W3211270166 hasConcept C106189395 @default.
- W3211270166 hasConcept C107457646 @default.
- W3211270166 hasConcept C119857082 @default.
- W3211270166 hasConcept C134306372 @default.
- W3211270166 hasConcept C149782125 @default.
- W3211270166 hasConcept C154945302 @default.
- W3211270166 hasConcept C159877910 @default.
- W3211270166 hasConcept C159886148 @default.
- W3211270166 hasConcept C162324750 @default.
- W3211270166 hasConcept C177148314 @default.
- W3211270166 hasConcept C179518139 @default.
- W3211270166 hasConcept C187736073 @default.
- W3211270166 hasConcept C199360897 @default.
- W3211270166 hasConcept C23224414 @default.
- W3211270166 hasConcept C2780451532 @default.
- W3211270166 hasConcept C33923547 @default.
- W3211270166 hasConcept C41008148 @default.
- W3211270166 hasConcept C95623464 @default.
- W3211270166 hasConcept C98045186 @default.
- W3211270166 hasConcept C98763669 @default.
- W3211270166 hasConceptScore W3211270166C105795698 @default.
- W3211270166 hasConceptScore W3211270166C106189395 @default.
- W3211270166 hasConceptScore W3211270166C107457646 @default.
- W3211270166 hasConceptScore W3211270166C119857082 @default.
- W3211270166 hasConceptScore W3211270166C134306372 @default.
- W3211270166 hasConceptScore W3211270166C149782125 @default.
- W3211270166 hasConceptScore W3211270166C154945302 @default.
- W3211270166 hasConceptScore W3211270166C159877910 @default.
- W3211270166 hasConceptScore W3211270166C159886148 @default.
- W3211270166 hasConceptScore W3211270166C162324750 @default.
- W3211270166 hasConceptScore W3211270166C177148314 @default.
- W3211270166 hasConceptScore W3211270166C179518139 @default.
- W3211270166 hasConceptScore W3211270166C187736073 @default.
- W3211270166 hasConceptScore W3211270166C199360897 @default.
- W3211270166 hasConceptScore W3211270166C23224414 @default.
- W3211270166 hasConceptScore W3211270166C2780451532 @default.
- W3211270166 hasConceptScore W3211270166C33923547 @default.
- W3211270166 hasConceptScore W3211270166C41008148 @default.
- W3211270166 hasConceptScore W3211270166C95623464 @default.
- W3211270166 hasConceptScore W3211270166C98045186 @default.
- W3211270166 hasConceptScore W3211270166C98763669 @default.
- W3211270166 hasLocation W32112701661 @default.
- W3211270166 hasLocation W32112701662 @default.