Timezone: »
Poster
Sample Efficient Reinforcement Learning via Low-Rank Matrix Estimation
Devavrat Shah · Dogyoon Song · Zhi Xu · Yuzhe Yang
We consider the question of learning $Q$-function in a sample efficient manner for reinforcement learning with continuous state and action spaces under a generative model. If $Q$-function is Lipschitz continuous, then the minimal sample complexity for estimating $\epsilon$-optimal $Q$-function is known to scale as $\Omega(\frac{1}{\epsilon^{d_1+d_2+2}})$ per classical non-parametric learning theory, where $d_1$ and $d_2$ denote the dimensions of the state and action spaces respectively. The $Q$-function, when viewed as a kernel, induces a Hilbert-Schmidt operator and hence possesses square-summable spectrum. This motivates us to consider a parametric class of $Q$-functions parameterized by its "rank" $r$, which contains all Lipschitz $Q$-functions as $r\to\infty$. As our key contribution, we develop a simple, iterative learning algorithm that finds $\epsilon$-optimal $Q$-function with sample complexity of $\widetilde{O}(\frac{1}{\epsilon^{\max(d_1, d_2)+2}})$ when the optimal $Q$-function has low rank $r$ and the discounting factor $\gamma$ is below a certain threshold. Thus, this provides an exponential improvement in sample complexity. To enable our result, we develop a novel Matrix Estimation algorithm that faithfully estimates an unknown low-rank matrix in the $\ell_\infty$ sense even in the presence of arbitrary bounded noise, which might be of interest in its own right. Empirical results on several stochastic control tasks confirm the efficacy of our "low-rank" algorithms.
Author Information
Devavrat Shah (Massachusetts Institute of Technology)
Devavrat Shah is a professor of Electrical Engineering & Computer Science and Director of Statistics and Data Science at MIT. He received PhD in Computer Science from Stanford. He received Erlang Prize from Applied Probability Society of INFORMS in 2010 and NeuIPS best paper award in 2008.
Dogyoon Song (Massachusetts Institute of Technology)
Zhi Xu (MIT)
Yuzhe Yang (MIT)
More from the Same Authors
-
2021 Spotlight: Regulating algorithmic filtering on social media »
Sarah Cen · Devavrat Shah -
2021 : Regret, stability, and fairness in matching markets with bandit learners »
Sarah Cen · Devavrat Shah -
2021 : Regret, stability, and fairness in matching markets with bandit learners »
Sarah Cen · Devavrat Shah -
2022 : A Causal Inference Framework for Network Interference with Panel Data »
Sarah Cen · Anish Agarwal · Christina Yu · Devavrat Shah -
2022 : On counterfactual inference with unobserved confounding »
Abhin Shah · Raaz Dwivedi · Devavrat Shah · Gregory Wornell -
2021 Poster: A Computationally Efficient Method for Learning Exponential Family Distributions »
Abhin Shah · Devavrat Shah · Gregory Wornell -
2021 Poster: Regulating algorithmic filtering on social media »
Sarah Cen · Devavrat Shah -
2021 Poster: Change Point Detection via Multivariate Singular Spectrum Analysis »
Arwa Alanqary · Abdullah Alomar · Devavrat Shah -
2021 Poster: PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators »
Anish Agarwal · Abdullah Alomar · Varkey Alumootil · Devavrat Shah · Dennis Shen · Zhi Xu · Cindy Yang -
2020 Poster: Estimation of Skill Distribution from a Tournament »
Ali Jadbabaie · Anuran Makur · Devavrat Shah -
2020 Poster: Rethinking the Value of Labels for Improving Class-Imbalanced Learning »
Yuzhe Yang · Zhi Xu -
2020 Spotlight: Estimation of Skill Distribution from a Tournament »
Ali Jadbabaie · Anuran Makur · Devavrat Shah -
2020 Demonstration: tspDB: Time Series Predict DB »
Anish Agarwal · Abdullah Alomar · Devavrat Shah -
2019 : Break / Poster Session 1 »
Antonia Marcu · Yao-Yuan Yang · Pascale Gourdeau · Chen Zhu · Thodoris Lykouris · Jianfeng Chi · Mark Kozdoba · Arjun Nitin Bhagoji · Xiaoxia Wu · Jay Nandy · Michael T Smith · Bingyang Wen · Yuege Xie · Konstantinos Pitas · Suprosanna Shit · Maksym Andriushchenko · Dingli Yu · GaĆ«l Letarte · Misha Khodak · Hussein Mozannar · Chara Podimata · James Foulds · Yizhen Wang · Huishuai Zhang · Ondrej Kuzelka · Alexander Levine · Nan Lu · Zakaria Mhammedi · Paul Viallard · Diana Cai · Lovedeep Gondara · James Lucas · Yasaman Mahdaviyeh · Aristide Baratin · Rishi Bommasani · Alessandro Barp · Andrew Ilyas · Kaiwen Wu · Jens Behrmann · Omar Rivasplata · Amir Nazemi · Aditi Raghunathan · Will Stephenson · Sahil Singla · Akhil Gupta · YooJung Choi · Yannic Kilcher · Clare Lyle · Edoardo Manino · Andrew Bennett · Zhi Xu · Niladri Chatterji · Emre Barut · Flavien Prost · Rodrigo Toro Icarte · Arno Blaas · Chulhee Yun · Sahin Lale · YiDing Jiang · Tharun Kumar Reddy Medini · Ashkan Rezaei · Alexander Meinke · Stephen Mell · Gary Kazantsev · Shivam Garg · Aradhana Sinha · Vishnu Lokhande · Geovani Rizk · Han Zhao · Aditya Kumar Akash · Jikai Hou · Ali Ghodsi · Matthias Hein · Tyler Sypherd · Yichen Yang · Anastasia Pentina · Pierre Gillot · Antoine Ledent · Guy Gur-Ari · Noah MacAulay · Tianzong Zhang -
2019 Poster: On Robustness of Principal Component Regression »
Anish Agarwal · Devavrat Shah · Dennis Shen · Dogyoon Song -
2019 Oral: On Robustness of Principal Component Regression »
Anish Agarwal · Devavrat Shah · Dennis Shen · Dogyoon Song -
2019 Tutorial: Synthetic Control »
Alberto Abadie · Vishal Misra · Devavrat Shah -
2018 Poster: Q-learning with Nearest Neighbors »
Devavrat Shah · Qiaomin Xie -
2017 Workshop: Nearest Neighbors for Modern Applications with Massive Data: An Age-old Solution with New Challenges »
George H Chen · Devavrat Shah · Christina Lee -
2017 Poster: Thy Friend is My Friend: Iterative Collaborative Filtering for Sparse Matrix Estimation »
Christian Borgs · Jennifer Chayes · Christina Lee · Devavrat Shah -
2016 Poster: Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering »
Dogyoon Song · Christina Lee · Yihua Li · Devavrat Shah -
2014 Workshop: Analysis of Rank Data: Confluence of Social Choice, Operations Research, and Machine Learning »
Shivani Agarwal · Hossein Azari Soufiani · Guy Bresler · Sewoong Oh · David Parkes · Arun Rajkumar · Devavrat Shah -
2014 Poster: Hardness of parameter estimation in graphical models »
Guy Bresler · David Gamarnik · Devavrat Shah -
2014 Poster: A Latent Source Model for Online Collaborative Filtering »
Guy Bresler · George H Chen · Devavrat Shah -
2014 Spotlight: A Latent Source Model for Online Collaborative Filtering »
Guy Bresler · George H Chen · Devavrat Shah -
2014 Poster: Learning Mixed Multinomial Logit Model from Ordinal Data »
Sewoong Oh · Devavrat Shah -
2014 Poster: Structure learning of antiferromagnetic Ising models »
Guy Bresler · David Gamarnik · Devavrat Shah -
2013 Workshop: Crowdsourcing: Theory, Algorithms and Applications »
Jennifer Wortman Vaughan · Greg Stoddard · Chien-Ju Ho · Adish Singla · Michael Bernstein · Devavrat Shah · Arpita Ghosh · Evgeniy Gabrilovich · Denny Zhou · Nikhil Devanur · Xi Chen · Alexander Ihler · Qiang Liu · Genevieve Patterson · Ashwinkumar Badanidiyuru Varadaraja · Hossein Azari Soufiani · Jacob Whitehill -
2013 Poster: A Latent Source Model for Nonparametric Time Series Classification »
George H Chen · Stanislav Nikolov · Devavrat Shah -
2013 Poster: Computing the Stationary Distribution Locally »
Christina Lee · Asuman Ozdaglar · Devavrat Shah -
2012 Poster: Iterative ranking from pair-wise comparisons »
Sahand N Negahban · Sewoong Oh · Devavrat Shah -
2012 Spotlight: Iterative ranking from pair-wise comparisons »
Sahand N Negahban · Sewoong Oh · Devavrat Shah -
2011 Poster: Iterative Learning for Reliable Crowdsourcing Systems »
David R Karger · Sewoong Oh · Devavrat Shah -
2011 Oral: Iterative Learning for Reliable Crowdsourcing Systems »
David R Karger · Sewoong Oh · Devavrat Shah -
2009 Poster: A Data-Driven Approach to Modeling Choice »
Vivek Farias · Srikanth Jagabathula · Devavrat Shah -
2009 Spotlight: A Data-Driven Approach to Modeling Choice »
Vivek Farias · Srikanth Jagabathula · Devavrat Shah -
2009 Poster: Local Rules for Global MAP: When Do They Work ? »
Kyomin Jung · Pushmeet Kohli · Devavrat Shah -
2008 Poster: Inferring rankings under constrained sensing »
Srikanth Jagabathula · Devavrat Shah -
2008 Oral: Inferring rankings under constrained sensing »
Srikanth Jagabathula · Devavrat Shah -
2007 Spotlight: Message Passing for Max-weight Independent Set »
Sujay Sanghavi · Devavrat Shah · Alan S Willsky -
2007 Poster: Message Passing for Max-weight Independent Set »
Sujay Sanghavi · Devavrat Shah · Alan S Willsky -
2007 Poster: Local Algorithms for Approximate Inference in Minor-Excluded Graphs »
Kyomin Jung · Devavrat Shah