"RL"的相关文档

标签“RL”的相关文档，共8条

Provably Efficient Algorithms for Multi-Objective Competitive RL
ProvablyEfﬁcientAlgorithmsforMulti-ObjectiveCompetitiveRLTianchengYu1YiTian1JingzhaoZhang1SuvritSra1Abstractaveragereturntoatargetsetsmallaslongasthissetsatisﬁesaconditioncalledapproachability(Bl...
for Efficient Algorithms Provably Multi-objective
2023-11-16 19:28:34549451.99 KB18
下载文档
On Reward-Free RL with Kernel and Neural Function Approximations Single-Agent MDP and Markov Game
OnReward-FreeRLwithKernelandNeuralFunctionApproximations:Single-AgentMDPandMarkovGameShuangQiu1JiepingYe1ZhaoranWang2ZhuoranYang3Abstractislargeandfunctionapproximatorssuchasneuralnetworksareemploy...
Neural Kernel and with on
2023-11-16 19:15:451156360.65 KB9
下载文档
LTL2Action Generalizing LTL Instructions for Multi-Task RL
LTL2Action:GeneralizingLTLInstructionsforMulti-TaskRLPashootanVaezipoor12AndrewC.Li12RodrigoToroIcarte12SheilaMcIlraith123Abstractapproachesdonotscalewellbecausetheyrequire(foreverypossibleenvironm...
for Multi-task Generalizing RL LTL2Action
2023-11-16 19:05:1111881.78 MB6
下载文档
Is Pessimism Provably Efficient for Offline RL
IsPessimismProvablyEfﬁcientforOfﬂineRL?YingJin1ZhuoranYang2ZhaoranWang3AbstractVinyalsetal.,2017)reliesontwoingredients:(i)expressivefunctionapproximators,e.g.,deepneuralnetworks(LeCunWestudyofﬂ...
for Efficient Provably is RL
2023-11-16 18:47:051601887.78 KB12
下载文档
Instabilities of Offline RL with Pre-Trained Neural Representation
InstabilitiesofOfﬂineRLwithPre-TrainedNeuralRepresentationRuosongWang1YifanWu1RuslanSalakhutdinov1ShamM.Kakade23Abstract2018;Wangetal.,2018;Yuetal.,2019);itisseeingmuchrecentinterestduetothelargea...
of Neural with RL Offline
2023-11-16 18:47:0411021.83 MB27
下载文档
Exponential Lower Bounds for Batch Reinforcement Learning Batch RL can be Exponentially Harder than Online RL
ExponentialLowerBoundsforBatchReinforcementLearning:BatchRLcanbeExponentiallyHarderthanOnlineRLAndreaZanette1AbstractweconsidertwoclassicalbatchRLproblems:1)theoff-policyevaluation(OPE)problem,wher...
for Reinforcement Batch bounds Exponential
2023-11-16 18:38:05906547.14 KB20
下载文档
Causal Curiosity RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
CausalCuriosity:RLAgentsDiscoveringSelf-supervisedExperimentsforCausalRepresentationLearningSumedhASontakke1ArashMehrjou2LaurentItti1BernhardSchölkopf2Abstractform.Thus,therehasbeenrecentinteresti...
Causal Self-supervised Discovering Experiments Agents
2023-11-16 18:11:1815812.52 MB8
下载文档
Provably efficient RL with Rich Observations via Latent State Decoding
ProvablyefﬁcientRLwithRichObservationsviaLatentStateDecodingSimonS.Du1AkshayKrishnamurthy2NanJiang3AlekhAgarwal4MiroslavDud´ık2JohnLangford2Abstract2010;Lattimore&Hutter,2012).Consequently,treat...
Efficient with via Provably Observations
2023-11-13 14:48:191859751.73 KB10
下载文档

首页上页 1 下页尾页