Timezone: »
Anca Dragan: Learning human preferences from language
Anca Dragan
Sat Dec 03 12:35 PM -- 01:05 PM (PST) @
In classic instruction following, language like "I'd like the JetBlue flight" maps to actions (e.g., selecting that flight). However, language also conveys information about a user's underlying reward function (e.g., a general preference for JetBlue), which can allow a model to carry out desirable actions in new contexts. In this talk, I'll share a model that infers rewards from language pragmatically: reasoning about how speakers choose utterances not only to elicit desired actions, but also to reveal information about their preferences.
Author Information
Anca Dragan (UC Berkeley)
More from the Same Authors
-
2021 : B-Pref: Benchmarking Preference-Based Reinforcement Learning »
Kimin Lee · Laura Smith · Anca Dragan · Pieter Abbeel -
2021 Spotlight: Pragmatic Image Compression for Human-in-the-Loop Decision-Making »
Sid Reddy · Anca Dragan · Sergey Levine -
2022 : Time-Efficient Reward Learning via Visually Assisted Cluster Ranking »
David Zhang · Micah Carroll · Andreea Bobu · Anca Dragan -
2022 : Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration »
Mesut Yang · Micah Carroll · Anca Dragan -
2022 : Aligning Robot Representations with Humans »
Andreea Bobu · Andi Peng · Pulkit Agrawal · Julie A Shah · Anca Dragan -
2022 Workshop: 5th Robot Learning Workshop: Trustworthy Robotics »
Alex Bewley · Roberto Calandra · Anca Dragan · Igor Gilitschenski · Emily Hannigan · Masha Itkina · Hamidreza Kasaei · Jens Kober · Danica Kragic · Nathan Lambert · Julien PEREZ · Fabio Ramos · Ransalu Senanayake · Jonathan Tompson · Vincent Vanhoucke · Markus Wulfmeier -
2022 Poster: First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization »
Siddharth Reddy · Sergey Levine · Anca Dragan -
2022 Poster: Uni[MASK]: Unified Inference in Sequential Decision Problems »
Micah Carroll · Orr Paradise · Jessy Lin · Raluca Georgescu · Mingfei Sun · David Bignell · Stephanie Milani · Katja Hofmann · Matthew Hausknecht · Anca Dragan · Sam Devlin -
2021 : Panel II: Machine decisions »
Anca Dragan · Karen Levy · Himabindu Lakkaraju · Ariel Rosenfeld · Maithra Raghu · Irene Y Chen -
2021 : BASALT: A MineRL Competition on Solving Human-Judged Task + Q&A »
Rohin Shah · Cody Wild · Steven Wang · Neel Alex · Brandon Houghton · William Guss · Sharada Mohanty · Stephanie Milani · Nicholay Topin · Pieter Abbeel · Stuart Russell · Anca Dragan -
2021 Poster: Pragmatic Image Compression for Human-in-the-Loop Decision-Making »
Sid Reddy · Anca Dragan · Sergey Levine -
2020 : Keynote: Anca Dragan »
Anca Dragan -
2020 : Mini-panel discussion 3 - Prioritizing Real World RL Challenges »
Chelsea Finn · Thomas Dietterich · Angela Schoellig · Anca Dragan · Anusha Nagabandi · Doina Precup -
2020 : Q&A for invited speaker, Anca Dragan »
Anca Dragan -
2020 : Getting human-robot interaction strategies to emerge from first principles »
Anca Dragan -
2020 Poster: AvE: Assistance via Empowerment »
Yuqing Du · Stas Tiomkin · Emre Kiciman · Daniel Polani · Pieter Abbeel · Anca Dragan -
2020 Poster: Reward-rational (implicit) choice: A unifying formalism for reward learning »
Hong Jun Jeon · Smitha Milli · Anca Dragan -
2020 Poster: Preference learning along multiple criteria: A game-theoretic perspective »
Kush Bhatia · Ashwin Pananjady · Peter Bartlett · Anca Dragan · Martin Wainwright -
2019 Workshop: Machine Learning for Autonomous Driving »
Rowan McAllister · Nicholas Rhinehart · Fisher Yu · Li Erran Li · Anca Dragan -
2019 Poster: On the Utility of Learning about Humans for Human-AI Coordination »
Micah Carroll · Rohin Shah · Mark Ho · Tom Griffiths · Sanjit Seshia · Pieter Abbeel · Anca Dragan -
2018 : Anca Dragan »
Anca Dragan -
2018 : Opening Remark »
Li Erran Li · Anca Dragan -
2018 Workshop: NIPS Workshop on Machine Learning for Intelligent Transportation Systems 2018 »
Li Erran Li · Anca Dragan · Juan Carlos Niebles · Silvio Savarese -
2018 : Anca Dragan »
Anca Dragan -
2018 Poster: Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior »
Sid Reddy · Anca Dragan · Sergey Levine -
2017 : Morning panel discussion »
Jürgen Schmidhuber · Noah Goodman · Anca Dragan · Pushmeet Kohli · Dhruv Batra -
2017 : "Communication via Physical Action" »
Anca Dragan -
2017 Workshop: 2017 NIPS Workshop on Machine Learning for Intelligent Transportation Systems »
Li Erran Li · Anca Dragan · Juan Carlos Niebles · Silvio Savarese -
2017 : Invited talk: Robot Transparency as Optimal Control »
Anca Dragan -
2016 : Learning Reliable Objectives »
Anca Dragan -
2016 : Invited Talk: Autonomous Cars that Coordinate with People (Anca Dragan, Berkeley) »
Anca Dragan -
2016 Poster: Cooperative Inverse Reinforcement Learning »
Dylan Hadfield-Menell · Stuart J Russell · Pieter Abbeel · Anca Dragan