Timezone: »
Website: https://sites.google.com/view/icml-i3
Abstract: A key challenge for deploying interactive machine learning systems in the real world is the ability for machines to understand human intent. Techniques such as imitation learning and inverse reinforcement learning are popular data-driven paradigms for modeling agent intentions and controlling agent behaviors, and have been applied to domains ranging from robotics and autonomous driving to dialogue systems. Such techniques provide a practical solution to specifying objectives to machine learning systems when they are difficult to program by hand.
While significant progress has been made in these areas, most research effort has concentrated on modeling and controlling single agents from dense demonstrations or feedback. However, the real world has multiple agents, and dense expert data collection can be prohibitively expensive. Surmounting these obstacles requires progress in frontiers such as:
1) the ability to infer intent from multiple modes of data, such as language or observation, in addition to traditional demonstrations.
2) the ability to model multiple agents and their intentions, both in cooperative and adversarial settings.
3) handling partial or incomplete information from the expert, such as demonstrations that lack dense action annotations, raw videos, etc..
The workshop on Imitation, Intention, and Interaction (I3) seeks contributions at the interface of these frontiers, and will bring together researchers from multiple disciplines such as robotics, imitation and reinforcement learning, cognitive science, AI safety, and natural language understanding. Our aim will be to reexamine the assumptions in standard imitation learning problem statements (e.g., inverse reinforcement learning) and connect distinct application disciplines, such as robotics and NLP, with researchers developing core imitation learning algorithms. In this way, we hope to arrive at new problem formulations, new research directions, and the development of new connections across distinct disciplines that interact with imitation learning methods.
Sat 8:45 a.m. - 9:00 a.m.
|
Welcoming Remarks
Video »
|
|
Sat 9:00 a.m. - 9:20 a.m.
|
Hal Daumé III
(Invited talk)
»
Title: Beyond demonstrations: Learning behavior from higher-level supervision |
|
Sat 9:20 a.m. - 9:40 a.m.
|
Joyce Chai
(Invited talk)
»
Video »
Title: Collaboration in Situated Language Communication |
|
Sat 9:40 a.m. - 10:00 a.m.
|
Stefano Ermon
(Invited talk)
»
Video »
Multi-agent Imitation and Inverse Reinforcement Learning |
|
Sat 10:00 a.m. - 10:20 a.m.
|
Iris R. Seaman
(Contributed talk)
»
Video »
Title: Nested Reasoning About Autonomous Agents Using Probabilistic Programs |
|
Sat 10:20 a.m. - 11:30 a.m.
|
Poster session and coffee
|
|
Sat 11:30 a.m. - 11:50 a.m.
|
Changyou Chen
(Contributed talk)
|
|
Sat 11:50 a.m. - 12:10 p.m.
|
Faraz Torabi
(Contributed talk)
Video »
|
|
Sat 12:10 p.m. - 12:30 p.m.
|
Seyed Kamyar Seyed Ghasemipour
(Contributed talk)
Video »
|
|
Sat 12:30 p.m. - 2:00 p.m.
|
Lunch break
|
|
Sat 2:05 p.m. - 2:25 p.m.
|
Natasha Jaques
(Invited talk)
»
Video »
Title: Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions. Causal influence is assessed using counterfactual reasoning. At each timestep, an agent simulates alternate actions that it could have taken, and computes their effect on the behavior of other agents. Actions that lead to bigger changes in other agents' behavior are considered influential and are rewarded. We show that this is equivalent to rewarding agents for having high mutual information between their actions. Empirical results demonstrate that influence leads to enhanced coordination and communication in challenging social dilemma environments, dramatically increasing the learning curves of the deep RL agents, and leading to more meaningful learned communication protocols. The influence rewards for all agents can be computed in a decentralized way by enabling agents to learn a model of other agents using deep neural networks. In contrast, key previous works on emergent communication in the MARL setting were unable to learn diverse policies in a decentralized manner and had to resort to centralized training. Consequently, the influence reward opens up a window of new opportunities for research in this area." |
|
Sat 2:25 p.m. - 2:45 p.m.
|
Pierre Sermanet
(Invited talk)
»
Video »
Title: Self-Supervision and Play Abstract: Real-world robotics is too complex to supervise with labels or through reward functions. While some amount of supervision is necessary, a more scalable approach instead is to bootstrap learning through self-supervision by first learning general task-agnostic representations. Specifically, we argue that we should learn from large amounts of unlabeled play data. Play serves as a way to explore and learn the breadth of what is possible in an undirected way. This strategy is widely used in nature to prepare oneself to achieve future tasks without knowing in advance which ones. In this talk, we present methods for learning vision and control representations entirely from unlabeled sequences. We demonstrate these representations self-arrange semantically and functionally and can be used for downstream tasks, without ever using labels or rewards. |
|
Sat 2:45 p.m. - 3:05 p.m.
|
Nicholas R Waytowich
(Contributed talk)
Video »
|
|
Sat 3:05 p.m. - 4:30 p.m.
|
Poster session and coffee
|
|
Sat 4:30 p.m. - 4:50 p.m.
|
Kris Kitani
(Invited talk)
»
Video »
Title: Multi-modal trajectory forecasting |
|
Sat 4:50 p.m. - 5:10 p.m.
|
Abhishek Das
(Contributed talk)
Video »
|
Author Information
Nicholas Rhinehart (Carnegie Mellon University)
Nick Rhinehart is a Ph.D. student at Carnegie Mellon University, focusing on understanding, forecasting, and controlling the behavior of agents through computer vision and machine learning. He is particularly interested in systems that learn to reason about the future. He has researched with Sergey Levine at UC Berkeley, Paul Vernaza at N.E.C. Labs, and Drew Bagnell at Uber ATG. His First-Person Forecasting work received the Marr Prize (Best Paper) Honorable Mention Award at ICCV 2017. Nick co-organized Tutorial on Inverse RL for Computer Vision at CVPR 2018 and is the primary organizer of ICML 2019 Workshop on Imitation, Intent, and Interaction.
Sergey Levine (UC Berkeley)

Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as computer vision and graphics. His research includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.
Chelsea Finn (Stanford, Google, UC Berkeley)

Chelsea Finn is a research scientist at Google Brain and a post-doctoral scholar at UC Berkeley. In September 2019, she will be joining Stanford's computer science department as an assistant professor. Finn's research interests lie in the ability to enable robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, Finn has developed deep learning algorithms for concurrently learning visual perception and control in robotic manipulation skills, inverse reinforcement methods for scalable acquisition of nonlinear reward functions, and meta-learning algorithms that can enable fast, few-shot adaptation in both visual perception and deep reinforcement learning. Finn received her Bachelors degree in EECS at MIT, and her PhD in CS at UC Berkeley. Her research has been recognized through an NSF graduate fellowship, a Facebook fellowship, the C.V. Ramamoorthy Distinguished Research Award, and the MIT Technology Review 35 under 35 Award, and her work has been covered by various media outlets, including the New York Times, Wired, and Bloomberg.
He He (NYU)
Ilya Kostrikov (NYU)
Justin Fu (University of California, Berkeley)
Siddharth Reddy (University of California, Berkeley)
More from the Same Authors
-
2020 Poster: Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions »
Michael Chang · Sid Kaushik · S. Matthew Weinberg · Thomas Griffiths · Sergey Levine -
2020 Poster: Learning Human Objectives by Evaluating Hypothetical Behavior »
Siddharth Reddy · Anca Dragan · Sergey Levine · Shane Legg · Jan Leike -
2020 Poster: Skew-Fit: State-Covering Self-Supervised Reinforcement Learning »
Vitchyr Pong · Murtaza Dalal · Steven Lin · Ashvin Nair · Shikhar Bahl · Sergey Levine -
2020 Poster: Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts? »
Angelos Filos · Panagiotis Tigas · Rowan McAllister · Nicholas Rhinehart · Sergey Levine · Yarin Gal -
2020 Poster: Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings »
Jesse Zhang · Brian Cheung · Chelsea Finn · Sergey Levine · Dinesh Jayaraman -
2019 Workshop: Workshop on Multi-Task and Lifelong Reinforcement Learning »
Sarath Chandar · Shagun Sodhani · Khimya Khetarpal · Tom Zahavy · Daniel J. Mankowitz · Shie Mannor · Balaraman Ravindran · Doina Precup · Chelsea Finn · Abhishek Gupta · Amy Zhang · Kyunghyun Cho · Andrei Rusu · Facebook Rob Fergus -
2019 Workshop: Generative Modeling and Model-Based Reasoning for Robotics and AI »
Aravind Rajeswaran · Emanuel Todorov · Igor Mordatch · William Agnew · Amy Zhang · Joelle Pineau · Michael Chang · Dumitru Erhan · Sergey Levine · Kimberly Stachenfeld · Marvin Zhang -
2019 Poster: Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables »
Kate Rakelly · Aurick Zhou · Chelsea Finn · Sergey Levine · Deirdre Quillen -
2019 Poster: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning »
Marvin Zhang · Sharad Vikram · Laura Smith · Pieter Abbeel · Matthew Johnson · Sergey Levine -
2019 Oral: Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables »
Kate Rakelly · Aurick Zhou · Chelsea Finn · Sergey Levine · Deirdre Quillen -
2019 Oral: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning »
Marvin Zhang · Sharad Vikram · Laura Smith · Pieter Abbeel · Matthew Johnson · Sergey Levine -
2019 Poster: Learning a Prior over Intent via Meta-Inverse Reinforcement Learning »
Kelvin Xu · Ellis Ratner · Anca Dragan · Sergey Levine · Chelsea Finn -
2019 Poster: EMI: Exploration with Mutual Information »
Hyoungseok Kim · Jaekyeom Kim · Yeonwoo Jeong · Sergey Levine · Hyun Oh Song -
2019 Poster: Online Meta-Learning »
Chelsea Finn · Aravind Rajeswaran · Sham Kakade · Sergey Levine -
2019 Poster: Diagnosing Bottlenecks in Deep Q-learning Algorithms »
Justin Fu · Aviral Kumar · Matthew Soh · Sergey Levine -
2019 Oral: Learning a Prior over Intent via Meta-Inverse Reinforcement Learning »
Kelvin Xu · Ellis Ratner · Anca Dragan · Sergey Levine · Chelsea Finn -
2019 Oral: EMI: Exploration with Mutual Information »
Hyoungseok Kim · Jaekyeom Kim · Yeonwoo Jeong · Sergey Levine · Hyun Oh Song -
2019 Oral: Diagnosing Bottlenecks in Deep Q-learning Algorithms »
Justin Fu · Aviral Kumar · Matthew Soh · Sergey Levine -
2019 Oral: Online Meta-Learning »
Chelsea Finn · Aravind Rajeswaran · Sham Kakade · Sergey Levine -
2019 Tutorial: Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning »
Chelsea Finn · Sergey Levine -
2018 Poster: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor »
Tuomas Haarnoja · Aurick Zhou · Pieter Abbeel · Sergey Levine -
2018 Poster: Regret Minimization for Partially Observable Deep Reinforcement Learning »
Peter Jin · EECS Kurt Keutzer · Sergey Levine -
2018 Poster: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Oral: Regret Minimization for Partially Observable Deep Reinforcement Learning »
Peter Jin · EECS Kurt Keutzer · Sergey Levine -
2018 Oral: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor »
Tuomas Haarnoja · Aurick Zhou · Pieter Abbeel · Sergey Levine -
2018 Oral: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Poster: Latent Space Policies for Hierarchical Reinforcement Learning »
Tuomas Haarnoja · Kristian Hartikainen · Pieter Abbeel · Sergey Levine -
2018 Poster: Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings »
John Co-Reyes · Yu Xuan Liu · Abhishek Gupta · Benjamin Eysenbach · Pieter Abbeel · Sergey Levine -
2018 Poster: Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control »
Aravind Srinivas · Allan Jabri · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2018 Oral: Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control »
Aravind Srinivas · Allan Jabri · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2018 Oral: Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings »
John Co-Reyes · Yu Xuan Liu · Abhishek Gupta · Benjamin Eysenbach · Pieter Abbeel · Sergey Levine -
2018 Oral: Latent Space Policies for Hierarchical Reinforcement Learning »
Tuomas Haarnoja · Kristian Hartikainen · Pieter Abbeel · Sergey Levine -
2017 Poster: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning »
Yevgen Chebotar · Karol Hausman · Marvin Zhang · Gaurav Sukhatme · Stefan Schaal · Sergey Levine -
2017 Talk: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning »
Yevgen Chebotar · Karol Hausman · Marvin Zhang · Gaurav Sukhatme · Stefan Schaal · Sergey Levine -
2017 Poster: Modular Multitask Reinforcement Learning with Policy Sketches »
Jacob Andreas · Dan Klein · Sergey Levine -
2017 Poster: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks »
Chelsea Finn · Pieter Abbeel · Sergey Levine -
2017 Poster: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Talk: Modular Multitask Reinforcement Learning with Policy Sketches »
Jacob Andreas · Dan Klein · Sergey Levine -
2017 Talk: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks »
Chelsea Finn · Pieter Abbeel · Sergey Levine -
2017 Talk: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Tutorial: Deep Reinforcement Learning, Decision Making, and Control »
Sergey Levine · Chelsea Finn