Meta tags:
keywords=your,keywords,goes,here;
author=Your Name;

Headings (most frequently used words):

tengyang, xie, publications, teaching, service,

Text of the page (most frequently used words):
learning (39), #tengyang (35), xie (35), pdf (32), arxiv (31), conference (25), neurips (16), icml (15), for (15), and (15), reinforcement (15), nan (15), jiang (15), machine (13), international (13), with (12), offline (10), the (10), information (10), processing (10), neural (9), systems (9), 2021 (7), 2024 (7), top (7), workshop (6), optimization (6), 2022 (6), research (6), iclr (6), wang (6), foster (6), ching (6), cheng (6), 2025 (6), online (5), dylan (5), representations (5), 2026 (4), from (4), journal (4), intelligence (4), efficient (4), spotlight (4), alexander (4), rakhlin (4), llm (4), science (4), 2018 (3), 2019 (3), theoretical (3), 2020 (3), feedback (3), 2023 (3), madison (3), mathematical (3), principles (3), teaching (3), poster (3), bai (3), xiang (3), policy (3), artificial (3), approximation (3), sample (3), john (3), langford (3), paul (3), mineiro (3), code (3), model (3), based (3), reasoning (3), via (3), preference (3), language (3), models (3), zeyu (3), jia (3), yurun (3), yuan (3), algorithms (3), university (3), program (2), committee (2), foundations (2), implicit (2), reviewer (2), statistical (2), association (2), ieee (2), transactions (2), analysis (2), acl (2), service (2), presentation (2), towards (2), batch (2), value (2), philip (2), amortila (2), kakade (2), wen (2), sun (2), ida (2), momennejad (2), interaction (2), grounded (2), xiong (2), alekh (2), agarwal (2), oral (2), bellman (2), blog (2), critic (2), akanksha (2), saran (2), action (2), mohak (2), bhardwaj (2), data (2), adversarial (2), harnessing (2), zhang (2), lee (2), findings (2), website (2), corby (2), rosset (2), ahmed (2), awadallah (2), direct (2), self (2), general (2), preferences (2), akshay (2), krishnamurthy (2), alignment (2), multi (2), step (2), fan (2), chen (2), publications (2), work (2), interests (2), was (2), microsoft (2), google (2), computer (2), new (2), template, andreas, viklund, real, life, organizer, interactive, human, american, jasa, jmlr, pattern, tpami, annals, statistics, theory, springer, proposals, aistats, aaai, ewrl, area, chair, colm, arr, rlc, fall, cs760, spring, cs839, indicates, equal, contribution, alphabetic, ordering, liu, yangyang, mohammad, ghavamzadeh, yinlam, chow, daoming, lyu, daesub, yoon, link, block, coordinate, ascent, algorithm, mean, variance, provably, low, switching, cost, yifei, causal, optimal, off, evaluation, marginalized, importance, sampling, uncertainty, uai, schemes, comparison, function, only, realizability, variant, lower, bound, discounted, setting, masatoshi, uehara, masaaki, imaizumi, nathan, kallus, submitted, finite, minimax, completeness, fast, rates, first, order, efficiency, add, supplement, huan, caiming, finetuning, bridging, slides, consistent, pessimism, outstanding, paper, runner, award, msr, adversarially, trained, actor, lekan, molu, complex, inclusive, armor, framework, improving, arbitrary, baseline, policies, sham, notable, role, coverage, byron, boots, dipendra, misra, alex, lamb, principled, representation, videos, ayush, sekhari, density, ratios, jianrui, cai, yong, jae, annual, meeting, computational, linguistics, countercurate, enhancing, physical, semantic, visio, linguistic, compositional, counterfactual, examples, fahim, tajwar, anikait, singh, archit, sharma, rafael, rafailov, jeff, schneider, stefano, ermon, chelsea, finn, aviral, kumar, fine, tuning, llms, should, leverage, suboptimal, arindam, mitra, michael, santacroce, technical, report, nash, improve, xpo, trainer, trl, exploratory, rlhf, sanjeev, kulkarni, mengdi, play, provable, scalable, haoxiang, wei, han, zhao, tong, empirical, methods, natural, emnlp, interpretable, objective, reward, modeling, mixture, experts, audrey, huang, wenhao, zhan, jason, correcting, mythos, regularization, without, overoptimization, chi, squared, need, verify, rethinking, process, supervision, perspective, reinforce, agent, reflection, trajectory, residual, minimization, simple, method, outcome, fundamental, limits, large, state, spaces, guarantees, xuanfei, ren, allen, nie, polca, stochastic, generative, breaking, capability, ceiling, post, training, reintroducing, markov, states, haoqun, cao, understanding, behavior, cloning, quantization, primary, goal, explore, design, relevant, agi, current, include, long, horizon, planning, control, decision, making, world, multimodality, assistant, professor, before, that, postdoctoral, researcher, received, where, fortunate, obtained, bachelor, degree, have, also, spent, time, simons, institute, amazon, technology, china, physics, illinois, urbana, champaign, york, city, england, wisconsin, wisc, edu, email, scholar, curriculum, vitæ,

Text of the page (random words):
tengyang xie publications teaching service curriculum vitæ google scholar email tx at cs wisc edu tengyang xie i am an assistant professor of computer science at university of wisconsin madison before that i was a postdoctoral researcher at microsoft research new england and new york city i received my ph d in computer science at university of illinois at urbana champaign where i was fortunate to work with nan jiang i obtained bachelor s degree in physics from university of science and technology of china i have also spent time at simons institute amazon ai microsoft research and google research research interests i work on reinforcement learning machine learning artificial intelligence the primary goal of my research is to explore the mathematical principles and design efficient algorithms relevant to artificial general intelligence agi my current interests include 1 long horizon planning and control 2 mathematical principles of reinforcement learning rl and decision making 3 world models and multimodality publications understanding behavior cloning with action quantization pdf arxiv haoqun cao tengyang xie international conference on machine learning icml 2026 breaking the capability ceiling of llm post training by reintroducing markov states pdf arxiv yurun yuan tengyang xie polca stochastic generative optimization with llm pdf arxiv code xuanfei ren allen nie tengyang xie ching an cheng international conference on machine learning icml 2026 offline reinforcement learning in large state spaces algorithms and guarantees pdf arxiv nan jiang tengyang xie statistical science outcome based online reinforcement learning algorithms and fundamental limits pdf arxiv fan chen zeyu jia alexander rakhlin tengyang xie conference on neural information processing systems neurips 2025 trajectory bellman residual minimization a simple value based method for llm reasoning pdf arxiv code yurun yuan fan chen zeyu jia alexander rakhlin tengyang xie conference on neural information processing systems neurips 2025 reinforce llm reasoning with multi agent reflection pdf arxiv yurun yuan tengyang xie international conference on machine learning icml 2025 do we need to verify step by step rethinking process supervision from a theoretical perspective pdf arxiv zeyu jia alexander rakhlin tengyang xie international conference on machine learning icml 2025 correcting the mythos of kl regularization direct alignment without overoptimization via chi squared preference optimization pdf arxiv audrey huang wenhao zhan tengyang xie jason d lee wen sun akshay krishnamurthy dylan j foster international conference on learning representations iclr 2025 spotlight top 5 1 interpretable preferences via multi objective reward modeling and mixture of experts pdf arxiv model blog haoxiang wang wei xiong tengyang xie han zhao tong zhang conference on empirical methods in natural language processing emnlp 2024 findings self play with adversarial critic provable and scalable offline alignment for language models pdf arxiv xiang ji sanjeev kulkarni mengdi wang tengyang xie exploratory preference optimization harnessing implicit q approximation for sample efficient rlhf pdf arxiv xpo trainer in trl tengyang xie dylan j foster akshay krishnamurthy corby rosset ahmed awadallah alexander rakhlin international conference on learning representations iclr 2025 direct nash optimization teaching language models to self improve with general preferences pdf arxiv corby rosset ching an cheng arindam mitra michael santacroce ahmed awadallah tengyang xie technical report 2024 preference fine tuning of llms should leverage suboptimal on policy data pdf arxiv website fahim tajwar anikait singh archit sharma rafael rafailov jeff schneider tengyang xie stefano ermon chelsea finn aviral kumar international conference on machine learning icml 2024 countercurate enhancing physical and semantic visio linguistic compositional reasoning via counterfactual examples pdf arxiv website jianrui zhang mu cai tengyang xie yong jae lee annual meeting of the association for computational linguistics acl 2024 findings harnessing density ratios for online reinforcement learning pdf arxiv philip amortila dylan j foster nan jiang ayush sekhari tengyang xie international conference on learning representations iclr 2024 spotlight top 5 towards principled representation learning from videos for reinforcement learning pdf arxiv dipendra misra akanksha saran tengyang xie alex lamb john langford international conference on learning representations iclr 2024 spotlight top 5 adversarial model for offline reinforcement learning pdf arxiv mohak bhardwaj tengyang xie byron boots nan jiang ching an cheng conference on neural information processing systems neurips 2023 the role of coverage in online reinforcement learning pdf arxiv tengyang xie dylan j foster yu bai nan jiang sham m kakade international conference on learning representations iclr 2023 notable top 5 oral top 1 8 armor a model based framework for improving arbitrary baseline policies with offline data pdf arxiv tengyang xie mohak bhardwaj nan jiang ching an cheng offline rl workshop at neurips 2022 interaction grounded learning with action inclusive feedback pdf arxiv tengyang xie akanksha saran dylan j foster lekan molu ida momennejad nan jiang paul mineiro john langford conference on neural information processing systems neurips 2022 complex feedback in online learning workshop at icml 2022 adversarially trained actor critic for offline reinforcement learning pdf arxiv code msr blog ching an cheng tengyang xie nan jiang alekh agarwal international conference on machine learning icml 2022 outstanding paper runner up award top 0 3 bellman consistent pessimism for offline reinforcement learning pdf arxiv slides tengyang xie ching an cheng nan jiang paul mineiro alekh agarwal conference on neural information processing systems neurips 2021 oral presentation top 0 6 policy finetuning bridging sample efficient offline and online reinforcement learning pdf arxiv tengyang xie nan jiang huan wang caiming xiong yu bai conference on neural information processing systems neurips 2021 interaction grounded learning pdf arxiv add l supplement tengyang xie john langford paul mineiro ida momennejad international conference on machine learning icml 2021 finite sample analysis of minimax offline reinforcement learning completeness fast rates and first order efficiency pdf arxiv masatoshi uehara masaaki imaizumi nan jiang nathan kallus wen sun tengyang xie submitted 2021 a variant of the wang foster kakade lower bound for the discounted setting pdf arxiv philip amortila nan jiang tengyang xie batch value function approximation with only realizability pdf arxiv tengyang xie nan jiang international conference on machine learning icml 2021 q approximation schemes for batch reinforcement learning a theoretical comparison pdf arxiv tengyang xie nan jiang conference on uncertainty in artificial intelligence uai 2020 towards optimal off policy evaluation for reinforcement learning with marginalized importance sampling pdf poster arxiv tengyang xie yifei ma yu xiang wang conference on neural information processing systems neurips 2019 spotlight presentation at the neurips 2018 workshop on causal learning provably efficient q learning with low switching cost pdf poster arxiv yu bai tengyang xie nan jiang yu xiang wang conference on neural information processing systems neurips 2019 a block coordinate ascent algorithm for mean variance optimization pdf poster link tengyang xie bo liu yangyang xu mohammad ghavamzadeh yinlam chow daoming lyu daesub yoon conference on neural information processing systems neurips 2018 indicates equal contribution or alphabetic ordering teaching cs839 mathematical principles of reinforcement learning spring 2026 uw madison cs760 machine learning fall 2024 uw madison service area chair neurips icml iclr colm acl arr rlc conference reviewer program committee icml workshop proposals neurips icml aistats aaai ewrl journal reviewer journal of the american statistical association jasa journal of machine learning research jmlr ieee transactions on pattern analysis and machine intelligence tpami annals of statistics ieee transactions on information theory springer machine learning journal workshop organizer interactive learning with implicit human feedback icml 2023 workshop program committee optimization foundations of rl neurips 2019 theoretical foundations of rl icml 2020 2021 offline rl neurips 2020 2022 rl for real life icml 2021 neurips 2022 2018 2026 tengyang xie template from andreas viklund