Timezone: »
In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correction terms which quantify the likelihood that the new policy will experience a certain state-action pair normalized by the probability with which the state-action pair appears in the dataset -- can improve accuracy and performance. In this work, we propose an algorithm, DualDICE, for estimating these quantities. In contrast to previous approaches, our algorithm is agnostic to knowledge of the behavior policy (or policies) used to generate the dataset. Furthermore, our algorithm eschews any direct use of importance weights, thus avoiding potential optimization instabilities endemic of previous methods. In addition to providing theoretical guarantees, we present an empirical study of our algorithm applied to off-policy policy evaluation and find that our algorithm significantly improves accuracy compared to existing techniques.
Author Information
Ofir Nachum (Google Brain)
Yinlam Chow (Google Research)
Bo Dai (Google Brain)
Lihong Li (Google Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Poster: DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections »
Wed Dec 11th 06:45 -- 08:45 PM Room East Exhibition Hall B + C
More from the Same Authors
-
2020 Poster: Off-Policy Imitation Learning from Observations »
Zhuangdi Zhu · Kaixiang Lin · Bo Dai · Jiayu Zhou -
2020 Poster: Differentiable Top-k with Optimal Transport »
Yujia Xie · Hanjun Dai · Minshuo Chen · Bo Dai · Tuo Zhao · Hongyuan Zha · Wei Wei · Tomas Pfister -
2020 Poster: Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration »
Hanjun Dai · Rishabh Singh · Bo Dai · Charles Sutton · Dale Schuurmans -
2020 Poster: Latent Bandits Revisited »
Joey Hong · Branislav Kveton · Manzil Zaheer · Yinlam Chow · Amr Ahmed · Craig Boutilier -
2020 Poster: Escaping the Gravitational Pull of Softmax »
Jincheng Mei · Chenjun Xiao · Bo Dai · Lihong Li · Csaba Szepesvari · Dale Schuurmans -
2020 Oral: Escaping the Gravitational Pull of Softmax »
Jincheng Mei · Chenjun Xiao · Bo Dai · Lihong Li · Csaba Szepesvari · Dale Schuurmans -
2020 Poster: Provably Efficient Neural Estimation of Structural Equation Models: An Adversarial Approach »
Luofeng Liao · You-Lin Chen · Zhuoran Yang · Bo Dai · Mladen Kolar · Zhaoran Wang -
2020 Poster: CoinDICE: Off-Policy Confidence Interval Estimation »
Bo Dai · Ofir Nachum · Yinlam Chow · Lihong Li · Csaba Szepesvari · Dale Schuurmans -
2020 Poster: Off-Policy Evaluation via the Regularized Lagrangian »
Mengjiao Yang · Ofir Nachum · Bo Dai · Lihong Li · Dale Schuurmans -
2020 Spotlight: CoinDICE: Off-Policy Confidence Interval Estimation »
Bo Dai · Ofir Nachum · Yinlam Chow · Lihong Li · Csaba Szepesvari · Dale Schuurmans -
2019 Workshop: The Optimization Foundations of Reinforcement Learning »
Bo Dai · Niao He · Nicolas Le Roux · Lihong Li · Dale Schuurmans · Martha White -
2019 Workshop: Safety and Robustness in Decision-making »
Mohammad Ghavamzadeh · Shie Mannor · Yisong Yue · Marek Petrik · Yinlam Chow -
2019 Poster: Meta Architecture Search »
Albert Shaw · Wei Wei · Weiyang Liu · Le Song · Bo Dai -
2019 Poster: A Kernel Loss for Solving the Bellman Equation »
Yihao Feng · Lihong Li · Qiang Liu -
2019 Poster: Exponential Family Estimation via Adversarial Dynamics Embedding »
Bo Dai · Zhen Liu · Hanjun Dai · Niao He · Arthur Gretton · Le Song · Dale Schuurmans -
2019 Poster: Energy-Inspired Models: Learning with Sampler-Induced Distributions »
John Lawson · George Tucker · Bo Dai · Rajesh Ranganath -
2019 Poster: Retrosynthesis Prediction with Conditional Graph Logic Network »
Hanjun Dai · Chengtao Li · Connor Coley · Bo Dai · Le Song -
2018 Poster: Cooperative neural networks (CoNN): Exploiting prior independence structure for improved classification »
Harsh Shrivastava · Eugene Bart · Bob Price · Hanjun Dai · Bo Dai · Srinivas Aluru -
2018 Poster: Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation »
Qiang Liu · Lihong Li · Ziyang Tang · Denny Zhou -
2018 Poster: A Lyapunov-based Approach to Safe Reinforcement Learning »
Yinlam Chow · Ofir Nachum · Edgar Duenez-Guzman · Mohammad Ghavamzadeh -
2018 Poster: Coupled Variational Bayes via Optimization Embedding »
Bo Dai · Hanjun Dai · Niao He · Weiyang Liu · Zhen Liu · Jianshu Chen · Lin Xiao · Le Song -
2018 Spotlight: Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation »
Qiang Liu · Lihong Li · Ziyang Tang · Denny Zhou -
2018 Poster: A Block Coordinate Ascent Algorithm for Mean-Variance Optimization »
Tengyang Xie · Bo Liu · Yangyang Xu · Mohammad Ghavamzadeh · Yinlam Chow · Daoming Lyu · Daesub Yoon -
2018 Poster: Predictive Approximate Bayesian Computation via Saddle Points »
Yingxiang Yang · Bo Dai · Negar Kiyavash · Niao He -
2018 Poster: Data-Efficient Hierarchical Reinforcement Learning »
Ofir Nachum · Shixiang (Shane) Gu · Honglak Lee · Sergey Levine -
2018 Poster: Adversarial Attacks on Stochastic Bandits »
Kwang-Sung Jun · Lihong Li · Yuzhe Ma · Jerry Zhu -
2018 Poster: Learning towards Minimum Hyperspherical Energy »
Weiyang Liu · Rongmei Lin · Zhen Liu · Lixin Liu · Zhiding Yu · Bo Dai · Le Song -
2017 Workshop: From 'What If?' To 'What Next?' : Causal Inference and Machine Learning for Intelligent Decision Making »
Ricardo Silva · Panagiotis Toulis · John Shawe-Taylor · Alexander Volfovsky · Thorsten Joachims · Lihong Li · Nathan Kallus · Adith Swaminathan -
2017 Poster: Bridging the Gap Between Value and Policy Based Reinforcement Learning »
Ofir Nachum · Mohammad Norouzi · Kelvin Xu · Dale Schuurmans -
2017 Poster: Deep Hyperspherical Learning »
Weiyang Liu · Yan-Ming Zhang · Xingguo Li · Zhiding Yu · Bo Dai · Tuo Zhao · Le Song -
2017 Spotlight: Deep Hyperspherical Learning »
Weiyang Liu · Yan-Ming Zhang · Xingguo Li · Zhiding Yu · Bo Dai · Tuo Zhao · Le Song -
2017 Poster: Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes »
Jianshu Chen · Chong Wang · Lin Xiao · Ji He · Lihong Li · Li Deng -
2016 Poster: Active Learning with Oracle Epiphany »
Tzu-Kuo Huang · Lihong Li · Ara Vartanian · Saleema Amershi · Jerry Zhu -
2014 Poster: Scalable Kernel Methods via Doubly Stochastic Gradients »
Bo Dai · Bo Xie · Niao He · Yingyu Liang · Anant Raj · Maria-Florina F Balcan · Le Song -
2013 Poster: Robust Low Rank Kernel Embeddings of Multivariate Distributions »
Le Song · Bo Dai -
2011 Poster: An Empirical Evaluation of Thompson Sampling »
Olivier Chapelle · Lihong Li -
2010 Spotlight: Learning from Logged Implicit Exploration Data »
Alex Strehl · Lihong Li · John Langford · Sham M Kakade -
2010 Poster: Learning from Logged Implicit Exploration Data »
Alexander L Strehl · John Langford · Lihong Li · Sham M Kakade -
2010 Poster: Parallelized Stochastic Gradient Descent »
Martin A Zinkevich · Markus Weimer · Alexander Smola · Lihong Li -
2008 Poster: Sparse Online Learning via Truncated Gradient »
John Langford · Lihong Li · Tong Zhang -
2008 Spotlight: Sparse Online Learning via Truncated Gradient »
John Langford · Lihong Li · Tong Zhang