Welcome to my page! Currently, I am an Associate Professor, leading the IAS (Intelligent Autonomous Systems) group in College of Electronic Engineering at Ocean University of China.
Before that, I was a PhD candidate at University of Amsterdam, a visiting scholar in Delft University of Technology, supervised by Shimon Whiteson and Hayley Hung. I was also a research intern at Honda Research Institute Japan. Right now, we are collaborating with HRI Japan and researching on the robot platform Haru.
Here is my CV and Google Scholar.
News
Dec 2025: Our paper “Transferring Policy of Offline Reinforcement Learning from Hybrid Dataset to Real World via Progressive Neural Network” has been accepted for publication in the IEEE Robotics and Automation Letters (RA-L). Congrats to Pengyu and Zheng!
November 2025: Our three papers: “Policy Generating and Value Shaping via Large Language Model for Long-Horizon Manipulation”, “Model-based Imitation Learning with Sim-to-real Transfer for Mobile Robot Navigation” and “Shaping Embodied Chatbot Haru Emotional Intelligence with Human Implicit Facial Feedback”, in collaboration with Randy Gomez and Eric Nichols of Honda Research Institute Japan, Shiqi Zhang from The State University of New York, were accepted for presentation at CCHI 2025. Congrats to Tongxu, Yohei, Ke, Enqi, Zicheng, Hongqi, Liu and Fanggeng!
November 2025: Our paper “Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation”, in collaboration with Professor Jianru Xue and Jianwu Fang of Xi’an Jiaotong University, was accepted for oral presentation at AAAI 2026. Congrats to Xuyang!
November 2025: Our paper “Multi-task learning for underwater robot via progressive neural network” was accepted for publication by Robot Learning Journal. Congrats to Xingwei and Song!
October 2025: I received the “Excellent Early-Career Board Member Award” of Robot Learning Journal.
October 2025: I am happy and honored to be invited to give a keynote talk on “Robot learning from simulation to reality for hybrid intelligence” at the 2025 International Conference on AI & Robotics “Ethics and Safety” held by the National Natural Science Foundation of China and the University of Hong Kong.
October 2025: Our paper “Improving Social Robot’s Emotional Intelligence with Physiological Feedback” was accepted for presentation at IEEE ROBIO 2025. Congrats to Yang!
September 2025: I am going to chair two sessions: one on “Safety HRI” and the other on “Robotic Imitation Learning” at IROS 2025. Please join us if you are interested!
September 2025: Congrats to Hao for his Master thesis winning the Chinese Association of Automation (CAA) Award.
August 2025: Our paper “Multi-AUV Coordination via Large Language Model-in-the-loop Generative Adversarial Interactive Self-Imitation Learning” was accepted for presentation as Late Breaking Result at IROS 2025. Congrats to Tian!
June 2025: Our IEEE RA-L paper “Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance” was accepted for presentation at IROS 2025.
June 2025: Our paper “Social Robot Haru Assisiting Dynamic Group Disscussion with Autonomous Eye Gaze Behavior” was accepted as oral presentation by IROS 2025. Congrats to Fei and Mingyang!
June 2025: Our paper “Imitation Learning from Observation for ROV Path Tracking” was accepted for pulication by Intelligent Marine Technology and Systems. Congrats to Jun and Song!
June 2025: Our paper “Social Robot Haru Imitating Human Gaze for Attention and Turn-taking Coordination in Multi-party Conversation” was accepted for presentation by ICSR 2025. Congrats to Liu!
March 2025: Congrats to Hao for his Master thesis being selected as excellent thesis of Shandong Province in China (山东省优硕).
February 2025: Our paper “Multi-Agent Generative Adversarial Interactive Self-Imitation Learning for AUV Formation Control and Obstacle Avoidance” has been accepted for publication in the IEEE Robotics and Automation Letters (RA-L). Congrats to Zheng, Tianhao and Tian!
December 2024: Our paper “Deep Reinforcement Learning from Human Preferences for ROV Path Tracking” has been accepted for publication in Ocean Engineering. Congrats to Shilong!
November 2024: Congrats to Fei for obtaining China National Scholarship! This is the highest honor of graduate students.
November 2024: Honda officially introduced our AI-powered social robot Haru.
November 2024: Congrats to Hao for his Master thesis being selected as excellent thesis in Ocean University of China.
November 2024: Shiqi (The State University of New York), Dachuan (Southern University of Science and Technology) and I have launched a special issue on “Learning Based Robot Path and Task Planning” at the journal Robot Learning. Please spread and submit your work to us! Thank you!
November 2024: I am happy and honored to be invited to give a talk on “Human-Machine Hybrid Learning with Sim-to-Real Transfer” at the Annual Conference of Hybrid Intelligence Professional Committee at China Automation Association.
October 2024: I am happy and honored to be appointed as a youth editorial board member of Robot Learning.
October 2024: I am happy and honored to be invited to give a talk on “Transferring robot learning from simulation to reality” at the Nanjing University-Ocean University of China “AI for Science” forum.
Septermber 2024: I am happy and honored to be appointed as a youth editorial board member of Intelligent Marine Technology and Systems.
September 2024: Our article “Embodied intelligence: Realizing full-body control of humanoid robots” has been published by Nature Machine Intelligence.
August 2024: Our group received a grant from Young Taishan Scholar Program. Congrats to IAS!
August 2024: I am happy and honored to be invited to give a talk at the Workshop on Nonverbal Cues for Human-Robot Cooperative Intelligence of IROS 2024.
August 2024: Our article “Embodied intelligence: Realizing full-body control of humanoid robots” has been accepted for publication by Nature Machine Intelligence.
June 2024: Our paper “Autonomous Storytelling for Social Robot with Human-Centered Reinforcement Learning” was accepted as oral presentation by IROS 2024. Congrats to Lei!
April 2024: I was very happy and honored to be invited to give a talk on “Embodied Social Intelligence” at Haru Fest 2024. Please join us at Haru Fest in Tokyo!
March 2024: The second Haru Fest — Haru Fest 2024 — is going to be held from May 8th to May 10th in Tokyo. It is right before ICRA 2024 in Yokohama. Please join us at Haru Fest!
March 2024: Our graduate student Fei Tang received a RAS Travel Grant to attend IEEE ICRA 2024. Congrats to Fei!
February 2024: Our paper “Imitation learning from imperfect demonstrations for AUV path tracking and obstacle avoidance” has been accepted for publication in Ocean Engineering. Congrats to Tianhao!
February 2024: Our paper “Transferring Meta-Policy from Simulation to Reality via Progressive Neural Network” has been accepted for publication in the IEEE Robotics and Automation Letters (RA-L). Congrats to Wei!
January 2024: Our two papers “Shaping Social Robot to Play Games with Human Demonstrations and Evaluative Feedback” and “Assisting Group Discussions Using Desktop Robot Haru” were accepted for presentation by IEEE ICRA 2024. Congrats to Chuanxiong and Fei!
December 2023: I am so honored and happy to have inspiring and interesting talks with undergraduate students in the “Mentor Afternoon Tea” program.
October 2023: Our paper “Emotional Understanding and Behavior Learning for Haru via Social Reinforcement Learning” was accepted for presentation by ICSR 2023. Congrats to Lei!
July 2023: We invited Shiqi Zhang from The State University of New York to give us a talk on “Leveraging Large Language Models for Robot Planning in Open Worlds”.
June 2023: Our paper “Model-based Adversarial Imitation Learning from Demonstrations and Human Reward” was accepted for presentation by IEEE/RSJ IROS 2023. Congrats to Jie and Jiangshan!
May 2023: Our two papers “Emotional Understanding for Social Robot Haru via Human-Centered Reinforcement Learning” and “Where to Look during Conversation: Autonomous Attentive Behavior Learning for Social Robot via Deep Reinforcement Learning” were accepted for oral presentation by ICRA 2023 Workshop: Towards a Balanced Cyberphysical Society: A Focus on Group Social Dynamics. Congrats to Lei and Fei!
May 2023: Our graduate student Jiangshan Hao received a RAS Travel Grant to attend IEEE ICRA 2023. Congrats to Jiangshan!
January 2023: Our two papers “Sim-to-Real Policy and Reward Transfer with Adaptive Forward Dynamics Model” and “GAN-Based Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback” were accepted for presentation by IEEE ICRA 2023. Congrats to Jie, Rongshun, Hao and Jiangshan!
December 2022: Our article “Transferring Policy of Deep Reinforcement Learning from Simulation to Reality for Robotics” has been published at Nature Machine Intelligence. Please refer to the full article via the link.
November 2022: Congrats to Dong, Zheng and Hui for obtaining China National Scholarship! This is the highest honor of graduate students.
October 2022: Our article “Transferring Policy of Deep Reinforcement Learning from Simulation to Reality for Robotics” has been accepted for publication by Nature Machine Intelligence. Congrats to Hao and Rongshun!
October 2022: Our two papers “Personalized Storytelling with Social Robot Haru” and “Imitating Human Strategy for Social Robot in Real-Time Two-Player Games” were accepted for presentation by ICSR 2022. Congrats to Hui and Chuanxiong!
August 2022: Our article “Autonomous Underwater Vehicle Formation Control and Obstacle Avoidance Using Multi-Agent Generative Adversarial Imitation Learning” was accepted for publication at Ocean Engineering.
July 2022: Our article “Generative Adversarial Interactive Imitation Learning for Path Following of Autonomous Underwater Vehicle” was accepted for publication at Ocean Engineering.
June 2022: Our paper “Affective Behavior Learning for Social Robot Haru with Implicit Evaluative Feedback” was accepted for presentation by IEEE IROS 2022.
May 2022: Our paper “Shaping Haru’s Affective Behavior with Valence and Arousal Based Implicit Facial Feedback” was accepted for presentation by IEEE RO-MAN 2022.
November 2021: Congrats to Zhen and Chunxi for obtaining China National Scholarship! This is the highest honor of graduate students.
July 2021: Our paper Shaping Progressive Net of Reinforcement Learning for Policy Transfer with Human Evaluative Feedback was accepted for presentation by IROS 2021.
June 2021: Our article Path Planning and Obstacle Avoidance for AUV: A Review was accepted for publication at Ocean Engineering.
June 2021: Our paper Shaping Affective Robot Haru’s Reactive Response was accepted for presentation by IEEE RO-MAN 2021.
Feb 2021: Our paper Automating Behavior Selection for Affective Telepresence Robot was accepted for presentation by ICRA 2021.
Feb 2021: Our paper Facial feedback for reinforcement learning: a case study and offline analysis using the TAMER framework was accepted for presentation at JAAMAS track of AAMAS 2021.
November 2020: Congrats to Jinying for obtaining China National Scholarship! This is the highest honor of graduate students.
Oct 2020: Haru was selected as one of case studies for UNICEF’s AI for children Project.
June 2020: Our paper Human Social Feedback for Efficient Interactive Reinforcement Agent Learning was accepted for presentation by IEEE RO-MAN 2020.
Feb 2020: Meet our big-eyed robot platform for studying social robotics — Haru. This is a collaborative research with Honda Research Institute Japan.
Feb 2020: Our article Facial feedback for reinforcement learning: a case study and offline analysis using the TAMER framework was accepted for publication in JAAMAS.
August 2019: Our article Human-Centered Reinforcement Learning: A Survey was now published by IEEE Transactions on Human-Machine Systems.
March 2019: Our article Human-Centered Reinforcement Learning: A Survey was accepted for publication by IEEE Transactions on Human-Machine Systems.
March 2019: The first SIRC consortium meeting was held at Robotics Co-research Lab of Honda Research Institute Japan in Tokyo. I was invited to give a talk on “Social Reinforcement Learning”.
October 2018: Our robot “Haru” was exhibited at IROS 2018 in Madrid for the first time. Please check out news about research of our consortium at Socially Intelligent Robotics Consortium (SIRC).
August 2018: Our paper “Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback” won Best Paper Award (Nanjing City Prize–Robotics Innovation Award) and UBTech Prize at ROMAN-2018.
August 2018: Our robot Haru was finally released. Check out the news by IEEE Spectrum.
June 2018: Our paper “Interactive Reinforcement Learning from Demonstration and Human Evaluative Feedback” was accepted by ROMAN-2018.
May 2018: I am going to give a talk about “Agents Interactively Learning from a Human Teacher” at workshop on Animated and Real Life Personal Robots @ ICRA 2018. Please join us in Brisbane!
December 2017: Our workshop on Animated and Real Life Personal Robots was accepted by ICRA 2018. Check out topics of our workshop at the site APR 2018. Please submit your work and join us in May 2018 at Brisbane!
September 2017: Our workshop on Robot Assistants was accepted by Humanoids 2017. Check out topics of our workshop at the site CAMERA 2017. Please submit your work and join us on November 15th 2017 at Birmingham!
July 2017: Our article Social interaction for efficient agent learning from human reward was accepted for publication in JAAMAS.
June 2016: I joined College of Information Science and Engineering at Ocean University of China as a lecturer.
May 26 2016: I successfully defended my thesis titled Socially Intelligent Autonomous Agents that Learn from Human Reward.
March 2016: Our paper Reinforcement Learning from Demonstration and Human Reward was accepted for presenting at workshop on Adaptive Learning Agents at AAMAS 2016.
January 2016: Our paper Towards Learning from Implicit Human Reward was accepted at AAMAS 2016 as a short paper.
September 2015: I am going to Honda Research Institute Japan as a research intern and will work on Machine Learning Methods for Multimodal Data to Improve Context-Aware of Personal Agent System.
September 2015: Our article “Using Informative Behavior to Increase Engagement While Learning from Human Reward” was published in JAAMAS now.
August 2015: Our article “Using Informative Behavior to Increase Engagement While Learning from Human Reward” was accepted for publication in JAAMAS.
January 2015: Our paper A Large-Scale Study of Agents Learning from Human Reward was accepted at AAMAS 2015 as a short paper.
October 2014: I am going to visit TU Delft from October 2014 to May 2015 and collaborate with Hamdi Dibeklioglu.
July 2014: Our study has been launched at NEMO Science Museum in Amsterdam. See here.
July 2014: We are invited to do an experiment in NEMO Science Museum in Amsterdam.
July 2014: Our paper Learning from Human Reward Benefit from Social-competitive Feedback was accepted for publication at ICDL-EpiRob 2014.
December 2013: Our paper Leveraging Social Networks to Motivate Humans to Train Agents was accepted at AAMAS 2014 as a short paper.
September 2013: I started organizing the IAS group meeting.
September 2013: Our students–Eugenio and Camiel (supervised by Diederik and I) will give a demo titled Decentralized Solutions and Tactics for RTS at BNAIC 2013.
July 2013: Check out our article Help the Facebook scientists: be a Tetris teacher on Computer Science For Fun (CS4FN), a magazine at Queen Mary University of London. Take part in our Facebook experiment!
June 2013: Participants needed for experiment!
Right now, our Facebook App–Intelligent Tetris is ready to play. It is about teaching an agent to play Tetris. Anybody who would like to take part in a scientific experiment and have fun at the same time, click the link and join us.
December 2012: Our paper Using Informative Behavior to Increase Engagement in the TAMER Framework was accepted at AAMAS 2013.
Guangliang Li (李光亮) 