Timezone: »
This tutorial will give an overview of the theoretical foundations of interactive decision making (high-dimensional/contextual bandits, reinforcement learning, and beyond), a promising paradigm for developing AI systems capable of intelligently exploring unknown environments. The tutorial will focus on connections and parallels between supervised learning/estimation and decision making, and will build on recent research which provides (i) sample complexity measures for interactive decision making that are necessary and sufficient for sample-efficient learning, and (ii) unified algorithm design principles that achieve optimal sample complexity. Using this unified approach as a foundation, the main aim of the tutorial will be to give a bird’s-eye view of the statistical landscape of reinforcement learning (e.g., what modeling assumptions lead to sample-efficient algorithms). Topics covered will range from basic challenges and solutions (exploration in tabular RL, policy gradient methods, contextual bandits) to the current frontier of understanding. We will also highlight practical algorithms.
Mon 10:00 a.m. - 10:55 a.m.
|
Bridging Learning and Decision Making: Part I
(
Tutorial
)
SlidesLive Video » |
Alexander Rakhlin 🔗 |
Mon 10:55 a.m. - 10:55 a.m.
|
Q&A
|
Dylan Foster · Alexander Rakhlin 🔗 |
Mon 11:00 a.m. - 11:55 a.m.
|
Bridging Learning and Decision Making: Part II
(
Tutorial
)
SlidesLive Video » |
Dylan Foster 🔗 |
Mon 11:55 a.m. - 12:00 p.m.
|
Q&A II
(
Q&A
)
|
Dylan Foster · Alexander Rakhlin 🔗 |
Author Information
Dylan Foster (Microsoft Research)
Alexander Rakhlin (MIT)
More from the Same Authors
-
2022 : Interaction-Grounded Learning with Action-inclusive Feedback »
Tengyang Xie · Akanksha Saran · Dylan Foster · Lekan Molu · Ida Momennejad · Nan Jiang · Paul Mineiro · John Langford -
2023 : When is Agnostic Reinforcement Learning Statistically Tractable? »
Gene Li · Zeyu Jia · Alexander Rakhlin · Ayush Sekhari · Nati Srebro -
2023 Poster: Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL »
Zakaria Mhammedi · Dylan Foster · Alexander Rakhlin -
2023 Oral: Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL »
Zakaria Mhammedi · Dylan Foster · Alexander Rakhlin -
2022 Poster: Contextual Bandits with Large Action Spaces: Made Practical »
Yinglun Zhu · Dylan Foster · John Langford · Paul Mineiro -
2022 Spotlight: Contextual Bandits with Large Action Spaces: Made Practical »
Yinglun Zhu · Dylan Foster · John Langford · Paul Mineiro -
2022 : Q&A II »
Dylan Foster · Alexander Rakhlin -
2022 : Q&A »
Dylan Foster · Alexander Rakhlin -
2022 : Bridging Learning and Decision Making: Part I »
Alexander Rakhlin -
2021 Poster: Top-k eXtreme Contextual Bandits with Arm Hierarchy »
Rajat Sen · Alexander Rakhlin · Lexing Ying · Rahul Kidambi · Dean Foster · Daniel Hill · Inderjit Dhillon -
2021 Spotlight: Top-k eXtreme Contextual Bandits with Arm Hierarchy »
Rajat Sen · Alexander Rakhlin · Lexing Ying · Rahul Kidambi · Dean Foster · Daniel Hill · Inderjit Dhillon -
2020 Poster: Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles »
Dylan Foster · Alexander Rakhlin -
2019 Poster: Near optimal finite time identification of arbitrary linear dynamical systems »
Tuhin Sarkar · Alexander Rakhlin -
2019 Oral: Near optimal finite time identification of arbitrary linear dynamical systems »
Tuhin Sarkar · Alexander Rakhlin