Timezone: »
This paper studies systematic exploration for reinforcement learning (RL) with rich observations and function approximation. We introduce contextual decision processes (CDPs), that unify most prior RL settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables tractable learning of near-optimal behavior in CDPs and is naturally small for many well-studied RL models. Our second contribution is a new RL algorithm that does systematic exploration to learn near-optimal behavior in CDPs with low Bellman rank. The algorithm requires a number of samples that is polynomial in all relevant parameters but independent of the number of unique contexts. Our approach uses Bellman error minimization with optimistic exploration and provides new insights into efficient exploration for RL with function approximation.
Author Information
Nan Jiang (Microsoft Research)
Akshay Krishnamurthy (UMass)
Alekh Agarwal (Microsoft Research)
John Langford (Microsoft Research)
Robert Schapire (Microsoft Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2017 Talk: Contextual Decision Processes with low Bellman rank are PAC-Learnable »
Tue Aug 8th 01:42 -- 02:00 AM Room C4.5
More from the Same Authors
-
2020 Workshop: Workshop on eXtreme Classification: Theory and Applications »
Anna Choromanska · John Langford · Maryam Majzoubi · Yashoteja Prabhu -
2020 Poster: Doubly robust off-policy evaluation with shrinkage »
Yi Su · Maria Dimakopoulou · Akshay Krishnamurthy · Miroslav Dudik -
2020 Poster: Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning »
Dipendra Misra · Mikael Henaff · Akshay Krishnamurthy · John Langford -
2020 Poster: Reward-Free Exploration for Reinforcement Learning »
Chi Jin · Akshay Krishnamurthy · Max Simchowitz · Tiancheng Yu -
2020 Poster: Adaptive Estimator Selection for Off-Policy Evaluation »
Yi Su · Pavithra Srinath · Akshay Krishnamurthy -
2020 Poster: Private Reinforcement Learning with PAC and Regret Guarantees »
Giuseppe Vietri · Borja de Balle Pigem · Akshay Krishnamurthy · Steven Wu -
2019 Poster: Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback »
Chicheng Zhang · Alekh Agarwal · Hal Daume · John Langford · Sahand Negahban -
2019 Poster: Fair Regression: Quantitative Definitions and Reduction-Based Algorithms »
Alekh Agarwal · Miroslav Dudik · Steven Wu -
2019 Oral: Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback »
Chicheng Zhang · Alekh Agarwal · Hal Daume · John Langford · Sahand Negahban -
2019 Oral: Fair Regression: Quantitative Definitions and Reduction-Based Algorithms »
Alekh Agarwal · Miroslav Dudik · Steven Wu -
2019 Poster: Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments »
Kirthevasan Kandasamy · Willie Neiswanger · Reed Zhang · Akshay Krishnamurthy · Jeff Schneider · Barnabás Póczos -
2019 Oral: Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments »
Kirthevasan Kandasamy · Willie Neiswanger · Reed Zhang · Akshay Krishnamurthy · Jeff Schneider · Barnabás Póczos -
2019 Poster: Provably efficient RL with Rich Observations via Latent State Decoding »
Simon Du · Akshay Krishnamurthy · Nan Jiang · Alekh Agarwal · Miroslav Dudik · John Langford -
2019 Poster: Contextual Memory Trees »
Wen Sun · Alina Beygelzimer · Hal Daume · John Langford · Paul Mineiro -
2019 Oral: Provably efficient RL with Rich Observations via Latent State Decoding »
Simon Du · Akshay Krishnamurthy · Nan Jiang · Alekh Agarwal · Miroslav Dudik · John Langford -
2019 Oral: Contextual Memory Trees »
Wen Sun · Alina Beygelzimer · Hal Daume · John Langford · Paul Mineiro -
2018 Poster: Semiparametric Contextual Bandits »
Akshay Krishnamurthy · Steven Wu · Vasilis Syrgkanis -
2018 Poster: Hierarchical Imitation and Reinforcement Learning »
Hoang Le · Nan Jiang · Alekh Agarwal · Miroslav Dudik · Yisong Yue · Hal Daume -
2018 Poster: A Reductions Approach to Fair Classification »
Alekh Agarwal · Alina Beygelzimer · Miroslav Dudik · John Langford · Hanna Wallach -
2018 Oral: Semiparametric Contextual Bandits »
Akshay Krishnamurthy · Steven Wu · Vasilis Syrgkanis -
2018 Oral: Hierarchical Imitation and Reinforcement Learning »
Hoang Le · Nan Jiang · Alekh Agarwal · Miroslav Dudik · Yisong Yue · Hal Daume -
2018 Oral: A Reductions Approach to Fair Classification »
Alekh Agarwal · Alina Beygelzimer · Miroslav Dudik · John Langford · Hanna Wallach -
2018 Poster: Practical Contextual Bandits with Regression Oracles »
Dylan Foster · Alekh Agarwal · Miroslav Dudik · Haipeng Luo · Robert Schapire -
2018 Oral: Practical Contextual Bandits with Regression Oracles »
Dylan Foster · Alekh Agarwal · Miroslav Dudik · Haipeng Luo · Robert Schapire -
2018 Poster: Learning Deep ResNet Blocks Sequentially using Boosting Theory »
Furong Huang · Jordan Ash · John Langford · Robert Schapire -
2018 Oral: Learning Deep ResNet Blocks Sequentially using Boosting Theory »
Furong Huang · Jordan Ash · John Langford · Robert Schapire -
2017 Poster: Optimal and Adaptive Off-policy Evaluation in Contextual Bandits »
Yu-Xiang Wang · Alekh Agarwal · Miroslav Dudik -
2017 Talk: Optimal and Adaptive Off-policy Evaluation in Contextual Bandits »
Yu-Xiang Wang · Alekh Agarwal · Miroslav Dudik -
2017 Poster: Logarithmic Time One-Against-Some »
Hal Daumé · Nikos Karampatziakis · John Langford · Paul Mineiro -
2017 Poster: Active Learning for Cost-Sensitive Classification »
Akshay Krishnamurthy · Alekh Agarwal · Tzu-Kuo Huang · Hal Daumé III · John Langford -
2017 Talk: Active Learning for Cost-Sensitive Classification »
Akshay Krishnamurthy · Alekh Agarwal · Tzu-Kuo Huang · Hal Daumé III · John Langford -
2017 Talk: Logarithmic Time One-Against-Some »
Hal Daumé · Nikos Karampatziakis · John Langford · Paul Mineiro -
2017 Tutorial: Real World Interactive Learning »
Alekh Agarwal · John Langford