Workshop

Human-AI Collaboration in Sequential Decision-Making

Besmira Nushi, Adish Singla, Sebastian Tschiatschek

Abstract:

A key challenge for the successful deployment of many real world human-facing automated sequential decision-making systems is the need for human-AI collaboration. Effective collaboration ensures that the complementary abilities and skills of the human-users and the AI system are leveraged to maximize utility. This is for instance important in applications such as autonomous driving, in which a human user’s skill might be required in safety critical situations, or virtual personal assistants, in which a human user can perform real-world physical interactions which the AI system cannot. Facilitating such collaboration requires cooperation, coordination, and communication, e.g., in the form of accountability, teaching interactions, provision of feedback, etc. Without effective human-AI collaboration, the utility of automated sequential decision-making systems can be severely limited. Thus there is a surge of interest in better facilitating human-AI collaboration in academia and industry. Most existing research has focussed only on basic approaches for human-AI collaboration with little focus on long-term interactions and the breadth needed for next-generation applications. In this workshop we bring together researchers to advance this important topic, focussing on the following three directions: (a) Accountability and trust; (b) Adaptive behavior for long-term collaboration; (c) Robust collaboration under mismatch.

Chat is not available.

Timezone: »

Schedule

Fri 5:55 a.m. - 6:00 a.m.
Introduction (Live)   
Fri 6:00 a.m. - 6:30 a.m.
Scaling up Probabilistic Safe Learning (Invited Talk)   
Scott Niekum
Fri 6:30 a.m. - 7:00 a.m.
Detecting and Influencing the Social Dynamics of a Human-Robot Team (Invited Talk)   
Sarah Sebo
Fri 7:00 a.m. - 7:10 a.m.
Break 1 (Break)
Fri 7:10 a.m. - 8:00 a.m.
Poster spotlight presentations 1 (Poster Spotlights)   
Sebastian Tschiatschek, Adish Singla, Besmira Nushi
Fri 8:00 a.m. - 9:00 a.m.
 link »

https://eventhosts.gather.town/rEmR7OowhlDHrLlC/humanai-poster-room-1t

A0: Kolby Nottingham, Anand Balakrishnan, Jyotirmoy Deshmukh and David Wingate, "Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning"

A1: Ishaan Shah, David Halpern, Michael Littman and Kavosh Asadi, "Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback"

A2: Vahid Balazadeh Meresht, Abir De, Adish Singla and Manuel Gomez Rodriguez, "Learning to Switch Among Agents in a Team"

A3: H M Sajjad Hossain, Yash Chandak, Soundararajan Srinivasan, David Koleczek, Weihao Tan, Siddhant Pradhan, Vishal Rohra, Vivek Chettiar, Aaslesha Rajaram, Nicholas Perello and Nan Ma, "Intervention Aware Shared Autonomy"

A4: Hengyuan Hu, Adam Lerer, Brandon Cui, David Wu, Luis Pineda, Noam Brown and Jakob Foerster, "Off Belief Learning"

A5: Brandon Cui, Hengyuan Hu, Luis Pineda and Jakob Foerster, "K-level Reasoning for Zero-Shot Coordination in Hanabi"

A6: Hamsa Bastani, Osbert Bastani and Wichinpong Sinchaisri, "Improving Human Decision-Making with Machine Learning"

B0: Interactive Grounded Language Understanding in a Collaborative Environment

Fri 9:00 a.m. - 9:30 a.m.
The Role of Conventions in Adaptive Human-AI Collaboration (Invited Talk)   
Dorsa Sadigh
Fri 9:30 a.m. - 10:00 a.m.
Towards Human-like and Collaborative AI in Video Games (Invited Talk)   
Katja Hofmann
Fri 10:00 a.m. - 10:10 a.m.
Break 2 (Break)
Fri 10:10 a.m. - 11:00 a.m.
Poster spotlight presentations 2 (Poster Spotlights)   
Sebastian Tschiatschek, Adish Singla, Besmira Nushi
Fri 11:00 a.m. - 12:00 p.m.
 link »

https://eventhosts.gather.town/RBepNDugnMC8rddK/humanai-poster-room-2t

A0: Jeevana Inala, Yecheng Ma, Osbert Bastani, Xin Zhang and Armando Solar-Lezama, "Safe Human-Interactive Control via Shielding"

A1: Jennifer Suriadinata, William Macke, Reuth Mirsky and Peter Stone, "Reasoning about Human Behavior in Ad Hoc Teamwork"

A2: Gottipati Vijaya Sai Krishna, Cloderic Mars, Greg Szriftgiser, Sagar Kurandwad, Francois Chabot and Vincent Robert, "Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment And Operations"

A3: Minori Narita, Sandhya Saisubramanian, Roderic A. Grupen and Shlomo Zilberstein, "Identifying Missing Features in State Representation for Safe Decision-Making"

A4: Hengyuan Hu, Samuel Sokota, David Wu, Anton Bakhtin, Andrei Lupu, Noam Brown and Jakob Foerster, "Self-Explaining Deviations for Zero-Shot Coordination"

A5: Aakriti Kumar, Trisha Patel, Aaron Benjamin and Mark Steyvers, "Explaining Algorithm Aversion with Metacognitive Bandits"

A6: Daniel Shin and Daniel Brown, "Offline Preference-Based Apprenticeship Learning"

B0: Wenshuo Guo, Kumar Agarwal, Aditya Grover, Vidya Muthukumar and Ashwin Pananjady, "Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits"

Fri 12:00 p.m. - 12:30 p.m.
Robust Robot Learning via Human-Guided Intermediate Representations (Invited Talk)   
Andreea Bobu
Fri 12:30 p.m. - 1:00 p.m.
Personalized Preference Learning - from Spinal Cord Stimulation to Exoskeletons (Invited Talk)   
Yisong Yue
Fri 1:00 p.m. - 1:05 p.m.
Concluding remarks (Conluding remarks)   
-
Using Logical Specifications of Objectives in Multi-Objective Reinforcement Learning (Poster) [ Visit Poster at Spot A0 in Virtual World ]  link » Kolby Nottingham
-
Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback (Poster) [ Visit Poster at Spot A1 in Virtual World ]  link » Ishaan Shah
-
Learning to Switch Among Agents in a Team (Poster) [ Visit Poster at Spot A2 in Virtual World ]  link » Manuel Gomez Rodriguez, Vahid Balazadeh Meresht
-
Intervention Aware Shared Autonomy (Poster) [ Visit Poster at Spot A3 in Virtual World ]  link » Weihao Tan
-
Off Belief Learning (Poster) [ Visit Poster at Spot A4 in Virtual World ]  link » Hengyuan Hu
-
K-level Reasoning for Zero-Shot Coordination in Hanabi (Poster) [ Visit Poster at Spot A5 in Virtual World ]  link » Brandon Cui
-
Improving Human Decision-Making with Machine Learning (Poster) [ Visit Poster at Spot A6 in Virtual World ]  link » Hamsa Bastani
-
Safe Human-Interactive Control via Shielding (Poster) [ Visit Poster at Spot A0 in Virtual World ]
Jeevana Priya Inala
-
Reasoning about Human Behavior in Ad Hoc Teamwork (Poster) [ Visit Poster at Spot A1 in Virtual World ]  link » Reuth Mirsky
-
Cogment: Open Source Framework For Distributed Multi-actor Training, Deployment And Operations (Poster) [ Visit Poster at Spot A2 in Virtual World ]
Sai Krishna Gottipati
-
Identifying Missing Features in State Representation for Safe Decision-Making (Poster) [ Visit Poster at Spot A3 in Virtual World ]  link » Minori Narita
-
Self-Explaining Deviations for Zero-Shot Coordination (Poster) [ Visit Poster at Spot A4 in Virtual World ]  link » Hengyuan Hu
-
Explaining Algorithm Aversion with Metacognitive Bandits (Poster) [ Visit Poster at Spot A5 in Virtual World ]  link » Aakriti Kumar
-
Offline Preference-Based Apprenticeship Learning (Poster) [ Visit Poster at Spot A6 in Virtual World ]  link » Daniel Shin
-
Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits (Poster) [ Visit Poster at Spot B0 in Virtual World ]  link » Wenshuo Guo
-
Interactive Grounded Language Understanding in a Collaborative Environment (Poster) [ Visit Poster at Spot B0 in Virtual World ]
Julia Kiseleva