Timezone: »
A central problem in dynamical system modeling is state discovery—that is, finding a compact summary of the past that captures the information needed to predict the future. Predictive State Representations (PSRs) enable clever spectral methods for state discovery; however, while consistent in the limit of infinite data, these methods often suffer from poor performance in the low data regime. In this paper we develop a novel algorithm for incorporating domain knowledge, in the form of an imperfect state representation, as side information to speed spectral learning for PSRs. We prove theoretical results characterizing the relevance of a user-provided state representation, and design spectral algorithms that can take advantage of a relevant representation. Our algorithm utilizes principal angles to extract the relevant components of the representation, and is robust to misspecification. Empirical evaluation on synthetic HMMs, an aircraft identification domain, and a gene splice dataset shows that, even with weak domain knowledge, the algorithm can significantly outperform standard PSR learning.
Author Information
Nan Jiang (University of Illinois at Urbana-Champaign)
Alex Kulesza (Google)
Satinder Singh (University of Michigan)
More from the Same Authors
-
2020 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · Chelsea Finn · Joelle Pineau · David Silver · Satinder Singh · Coline Devin · Misha Laskin · Kimin Lee · Janarthanan Rajendran · Vivek Veeriah -
2020 Poster: Minimax Value Interval for Off-Policy Evaluation and Policy Optimization »
Nan Jiang · Jiawei Huang -
2019 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · Chelsea Finn · Joelle Pineau · David Silver · Satinder Singh · Joshua Achiam · Carlos Florensa · Christopher Grimm · Haoran Tang · Vivek Veeriah -
2019 Poster: Differentially Private Covariance Estimation »
Kareem Amin · Travis Dick · Alex Kulesza · Andres Munoz · Sergei Vassilvitskii -
2019 Poster: Discovery of Useful Questions as Auxiliary Tasks »
Vivek Veeriah · Matteo Hessel · Zhongwen Xu · Janarthanan Rajendran · Richard L Lewis · Junhyuk Oh · Hado van Hasselt · David Silver · Satinder Singh -
2019 Poster: No-Press Diplomacy: Modeling Multi-Agent Gameplay »
Philip Paquette · Yuchen Lu · SETON STEVEN BOCCO · Max Smith · Satya O.-G. · Jonathan K. Kummerfeld · Joelle Pineau · Satinder Singh · Aaron Courville -
2019 Poster: Provably Efficient Q-Learning with Low Switching Cost »
Yu Bai · Tengyang Xie · Nan Jiang · Yu-Xiang Wang -
2018 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · David Silver · Satinder Singh · Joelle Pineau · Joshua Achiam · Rein Houthooft · Aravind Srinivas -
2018 Poster: On Learning Intrinsic Rewards for Policy Gradient Methods »
Zeyu Zheng · Junhyuk Oh · Satinder Singh -
2018 Poster: Maximizing Induced Cardinality Under a Determinantal Point Process »
Jennifer Gillenwater · Alex Kulesza · Sergei Vassilvitskii · Zelda Mariet -
2018 Poster: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2018 Spotlight: On Oracle-Efficient PAC RL with Rich Observations »
Christoph Dann · Nan Jiang · Akshay Krishnamurthy · Alekh Agarwal · John Langford · Robert Schapire -
2017 Symposium: Deep Reinforcement Learning »
Pieter Abbeel · Yan Duan · David Silver · Satinder Singh · Junhyuk Oh · Rein Houthooft -
2017 Poster: Repeated Inverse Reinforcement Learning »
Kareem Amin · Nan Jiang · Satinder Singh -
2017 Spotlight: Repeated Inverse Reinforcement Learning »
Kareem Amin · Nan Jiang · Satinder Singh -
2017 Poster: Value Prediction Network »
Junhyuk Oh · Satinder Singh · Honglak Lee -
2016 Workshop: Deep Reinforcement Learning »
David Silver · Satinder Singh · Pieter Abbeel · Peter Chen -
2015 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · John Schulman · Satinder Singh · David Silver -
2015 Poster: Action-Conditional Video Prediction using Deep Networks in Atari Games »
Junhyuk Oh · Xiaoxiao Guo · Honglak Lee · Richard L Lewis · Satinder Singh -
2015 Spotlight: Action-Conditional Video Prediction using Deep Networks in Atari Games »
Junhyuk Oh · Xiaoxiao Guo · Honglak Lee · Richard L Lewis · Satinder Singh -
2014 Workshop: From Bad Models to Good Policies (Sequential Decision Making under Uncertainty) »
Odalric-Ambrym Maillard · Timothy A Mann · Shie Mannor · Jeremie Mary · Laurent Orseau · Thomas Dietterich · Ronald Ortner · Peter Grünwald · Joelle Pineau · Raphael Fonteneau · Georgios Theocharous · Esteban D Arcaute · Christos Dimitrakakis · Nan Jiang · Doina Precup · Pierre-Luc Bacon · Marek Petrik · Aviv Tamar -
2014 Poster: Deep Learning for Real-Time Atari Game Play Using Offline Monte-Carlo Tree Search Planning »
Xiaoxiao Guo · Satinder Singh · Honglak Lee · Richard L Lewis · Xiaoshi Wang -
2013 Poster: Reward Mapping for Transfer in Long-Lived Agents »
Xiaoxiao Guo · Satinder Singh · Richard L Lewis -
2013 Session: Oral Session 9 »
Satinder Singh -
2010 Poster: Reward Design via Online Gradient Ascent »
Jonathan D Sorg · Satinder Singh · Richard L Lewis -
2008 Poster: Simple Local Models for Complex Dynamical Systems »
Erik Talvitie · Satinder Singh -
2008 Oral: Simple Local Models for Complex Dynamical Systems »
Erik Talvitie · Satinder Singh -
2007 Oral: Exponential Family Predictive Representations of State »
David Wingate · Satinder Singh -
2007 Poster: Exponential Family Predictive Representations of State »
David Wingate · Satinder Singh