Workshop on Human-aligned Reinforcement Learning for Autonomous Agents and Robots

This workshop was held at F203 at Annex Hall.

Yokohama timezone	Speaker	Topic
09:00-09:15	Welcome and introduction
09:15-10:00 Video here	Georgia Chalvatzaki	Safe and Coordinated Human-Robot Interactions
10:00-10:30	Coffee break and poster session
10:30-11:15 Video here	Matthew Gombolay	Interpretable and Interactive Reinforcement Learning in Human-Robot Teaming
11:15-12:00 Video here	Dana Kulić	Reinforcement Learning for HRI: The Role of Simulations
12:00-13:30	Lunch Break
13:30-14:00 Video here	Contribution Talks Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies Adaptive Robot Navigation: A Human-Centered and Multi-Objective Approach with Demonstrations Learning Interactive Viewpoint Planning for Foresighted Object Discovery Considering Human Preferences



14:00-14:45 Video here	Eiji Uchibe	Human-in-the-loop Policy Learning by Co-Evolution of Human and Generative Imitation Learning
14:45-15:30 Video here	Pulkit Agrawal	Human-in-the-loop Sensorimotor Learning
15:30-16:00	Coffee break and poster session
16:00-16:45 Video here	Panel Discussion
16:45-17:00	Farewell and conclusions

Best Workshop paper:

Authors	Title
Jorge de Heuvel, Tharun Sethuraman and Maren Bennewitz	Adaptive Robot Navigation: A Human-Centered and Multi-Objective Approach with Demonstrations

Runner-Up: Best papers

Authors	Title
Finn Rietz, Erik Schaffernicht, Stefan Heinrich and Johannes Andreas Stork	Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies
Nils Dengler, Sicong Pan, Vamsi Kalagaturu, Rohit Menon, Murad Dawood and Maren Bennewitz	Learning Interactive Viewpoint Planning for Foresighted Object Discovery Considering Human Preferences

Accepted papers:

Authors	Title
Finn Rietz, Erik Schaffernicht, Stefan Heinrich and Johannes Andreas Stork	Towards Interpretable Reinforcement Learning with Constrained Normalizing Flow Policies
Liqun Zhao, Keyan Miao, Konstantinos Gatsis and Antonis Papachristodoulou	NLBAC: A Neural Ordinary Differential Equations-based Framework for Stable and Safe Reinforcement Learning in Human-aligned Tasks
Homayoun Honari, Mehran Ghafarian Tamizi and Homayoun Najjaran	Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization
Ajsal Shereef Palattuparambil, Thommen George Karimpanal and Santu Rana	Zero-shot Personalisation via Dynamic Policy Fusion
William Z. Ye, Eduardo B. Sandoval, Pamela Carreno-Medrano and Francisco Cruz	Contextual Affordances for Safe Exploration in Robotic Scenarios
Jorge de Heuvel, Tharun Sethuraman and Maren Bennewitz	Adaptive Robot Navigation: A Human-Centered and Multi-Objective Approach with Demonstrations
Nils Dengler, Sicong Pan, Vamsi Kalagaturu, Rohit Menon, Murad Dawood and Maren Bennewitz	Learning Interactive Viewpoint Planning for Foresighted Object Discovery Considering Human Preferences
Mauro Martini, Noé Pérez-Higueras, Andrea Ostuni, Marcello Chiaberge, Fernando Caballero Benítez and Luis Merino	Adaptive Human-Aware Local Planner with Reinforcement Learning
Chanin Eom, Dongsu Lee and Minhae Kwon	Imperfect Dataset is Enough: Reinforcement Learning with Selective Imitation from Prior Data
Carlos Gutierrez-Alvarez, Rafael Flor-Rodríguez-Rabadán, Asako Kanezaki and Roberto Javier López-Sastre	OffNav: Offline Reinforcement Learning for Visual Semantic Navigation