"Benchmark"的相关文档

TeachMyAgent a Benchmark for Automatic Curriculum Learning in Deep RL
TeachMyAgent:aBenchmarkforAutomaticCurriculumLearninginDeepRLCle´mentRomac1Re´myPortelas1KatjaHofmann2Pierre-YvesOudeyer1Abstractagentisunlikelytobeoptimalforcomplexlearningprob-lems.Buildingupon...
Learning for Curriculum Automatic in
2023-11-16 19:42:0113181.23 MB18
下载文档
WILDS A Benchmark of in-the-Wild Distribution Shifts
WILDS:ABenchmarkofin-the-WildDistributionShiftsPangWeiKoh1ShioriSagawa1HenrikMarklund1SangMichaelXie1MarvinZhang2AkshayBalsubramani1WeihuaHu1MichihiroYasunaga1RichardLanasPhillips3IrenaGao1TonyLee1...
of Distribution Benchmark Shifts WILDS
2023-11-16 19:41:277233.16 MB27
下载文档
CURI A Benchmark for Productive Concept Learning Under Uncertainty
CURI:ABenchmarkforProductiveConceptLearningunderUncertaintyRamakrishnaVedantam1ArthurSzlam1MaximilianNickel1AriMorcos1BrendenLake12Abstracttotakefromone’sapartmentinaﬁre”(children,dogs,keep-sake...
Learning for under Benchmark Concept
2023-11-16 18:30:559923.49 MB5
下载文档
AGENT A Benchmark for Core Psychological Reasoning
AGENT:ABenchmarkforCorePsychologicalReasoningTianminShu1AbhishekBhandwaldar2ChuangGan2KevinA.Smith1ShariLiu1DanGutfreund2ElizabethSpelke3JoshuaB.Tenenbaum1TomerD.Ullman3AbstractGoalobjectsObstacles...
for Reasoning Agent Benchmark Core
2023-11-16 18:00:2716343.19 MB7
下载文档
A large-scale Benchmark for few-shot program induction and synthesis
Alarge-scaleBenchmarkforfew-shotprograminductionandsynthesisFerranAlet1JavierLopez-Contreras1JamesKoppel1MaxwellNye1ArmandoSolar-Lezama1TomásLozano-Pérez1LesliePackKaelbling1JoshuaB.Tenenbaum1Abs...
for and Large-Scale Program Few-shot
2023-11-16 17:52:041802827.47 KB7
下载文档
Leveraging Procedural Generation to Benchmark Reinforcement Learning
LeveragingProceduralGenerationtoBenchmarkReinforcementLearningKarlCobbe1ChristopherHesse1JacobHilton1JohnSchulman1Abstractoraretheyapproximatelymemorizingspeciﬁctrajectories?WeintroduceProcgenBenc...
Learning Generation Reinforcement to Leveraging
2023-11-14 21:45:0119732.12 MB2
下载文档
Agent57 Outperforming the Atari Human Benchmark
Agent57:OutperformingtheAtariHumanBenchmarkAdriàPuigdomènechBadia1BilalPiot1StevenKapturowski1PabloSprechmann1AlexVitvitskyi1DanielGuo1CharlesBlundell1AbstractFigure1.Numberofgameswherealgorithms...
the Human Agent57 Outperforming Atari
2023-11-14 21:43:021782977.3 KB19
下载文档