Research
I work at intersection of machine learning and robotics. My research aims to make AI systems more reliable and useful by making them more robust, creative, general-purpose and have the ability to continuously improve. I believe open-ended learning systems which can continously learn and generate intersting things can be a solution to this. To enable such systems, I study Quality-Diversity algorithms which encourages novelty and diversity as a key component in the process. More specifically, I am interested in the synergy between deep models (i.e. generative/foundation models) and Quality-Diversity search which can lead to self-improvement.
|
News
- [5/2024] In-context QD: our work on many-shot in-context learning with high-quality and diverse (Quality-Diverse) examples was accepted at ALIFE 2024!
- [12/2023] Our work on accounting for policy reproducibility when evaluating RL algorithms was accepted at AAAI!
- [6/2023] Check out our work on using RL for behavioural diversity of a quadruped, including dynamic and agile three-legged locomotion behaviour. Video here! Interestingly similar athletic intelligence and adaptability to that of animals!
- [4/2023] GDAQD accepted at ALIFE 2023!
- [3/2023] Two papers and a poster accepted at GECCO 2023. Going to be a fun summer week in Lisbon!
- [1/2023] Our work studying QD-based neuroevolution and unsupervised deep RL methods was accepted at ICLR 2023! Grateful to be able to work with such a great team of collaborators on this one!
- [1/2023] One paper accepted at ICRA 2023. See you in London!
- [12/2022] Will be presenting our work on scaling model-based QD with gradient updates at the NeurIPS Deep Reinforcement Learning Workshop!
- [7/2022] We officially released QDax, an open-source library in JAX for Quality-Diversity and Population-based algorithms. Check it out!
- [3/2022] I was awarded the Imperial College Robotics Forum - Amazon PhD Prize for Outstanding Achievement in Robotics!
- [3/2022] Will be presenting 2 papers at the Agent Learning in Open-Endedness Workshop at ICLR 2022. We will present QDax in a spotlight talk!
- [3/2022] 1 paper and 1 poster accepted to GECCO 2022! Excited to be heading back to Boston!
- [1/2022] DA-QD accepted at ICRA 2022! My first paper since strating the PhD!
|
|
Large Language Models as In-context AI Generators for Quality-Diversity
Bryan Lim, Manon Flageat, Antoine Cully
Conference on Artificial Life (ALIFE), 2024
(arXiv)
|
|
Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
M.Flageat*, Bryan Lim*, A. Cully
The Genetic and Evolutionary Computation Conference (GECCO), 2024
(arXiv)
(project page)
|
|
Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms
M.Flageat*, Bryan Lim*, A. Cully
AAAI Conference on Artificial Intelligence (AAAI), 2023
(arXiv)
|
|
Quality-Diversity Optimization on a Physical Robot through Dynamics-Aware and Reset-free Learning
S. Smith, Bryan Lim, H. Janmohamed, A. Cully
The Genetic and Evolutionary Computation Conference (GECCO) - Poster, 2023
(arXiv)
(video)
|
|
Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains
L.Grillotti*, M.Flageat*, Bryan Lim, A. Cully
The Genetic and Evolutionary Computation Conference (GECCO), 2023
(arXiv)
|
|
Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
Bryan Lim*, M.Flageat*, A. Cully
The Genetic and Evolutionary Computation Conference (GECCO), 2023
(arXiv)
|
|
Efficient Exploration using Model-Based Quality-Diversity with Gradients
Bryan Lim*, M.Flageat*, A. Cully
Conference on Artificial Life (ALIFE), 2023
Deep Reinforcement Learning Workshop, NeurIPS, 2022
(arXiv)
(video)
|
|
Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
F. Chalumeau*, R. Boige*, Bryan Lim, V. Macé, M. Allard, A. Flajolet, A. Cully, T. Pierrot
International Conference on Learning Representations (ICLR) (Spotlight), 2023
(arXiv)
|
|
Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors
Shikha Surana*, Bryan Lim*, Antoine Cully
International Conference on Robotics and Automation (ICRA), 2023
(arXiv)
|
|
Accelerated Quality-Diversity through Massive Parallelism
Bryan Lim, Maxime Allard, Luca Grillotti, Antoine Cully
Transactions on Machine Learning Research (TMLR), 2023
Agent Learning in Open-Endedness Workshop, ICLR (Spotlight), 2022
The Genetic and Evolutionary Computation Conference (GECCO) - Poster, 2022
(arXiv)
(code)
|
|
Learning to Walk Autonomously via Reset-Free Quality-Diversity
Bryan Lim*, Alexander Reichenbach*, Antoine Cully
The Genetic and Evolutionary Computation Conference (GECCO), 2022
Agent Learning in Open-Endedness Workshop, ICLR, 2022
(arXiv)
(project page)
|
|
Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires
Bryan Lim, Luca Grillotti, Lorenzo Bernasconi, Antoine Cully
International Conference on Robotics and Automation (ICRA), 2022
(arXiv)
(code)
(project page)
|
|
Tactile object pose estimation from the first touch with geometric contact rendering
M Bauza, E Valls, Bryan Lim, T Sechopoulos, A Rodriguez
Conference on Robot Learning (CoRL), 2020
(arXiv)
(video)
(project page)
|
|
Robust Autonomous Navigation of a Small-Scale Quadruped Robot in Real-World Environments
T Dudzik, M Chignoli, G Bledt, Bryan Lim, A Miller, D Kim, S Kim
International Conference on Intelligent Robots and Systems (IROS), 2020
(paper)
|
|
Vision aided dynamic exploration of unstructured terrain with a small-scale quadruped robot
D Kim, D Carballo, J Di Carlo, B Katz, G Bledt, Bryan Lim, S Kim
International Conference on Robotics and Automation (ICRA), 2020
(video)
(paper)
|
|
QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
Felix Chalumeau*, Bryan Lim*, Raphaël Boige, Maxime Allard, Luca Grillotti, Manon Flageat, Valentin Macé, Guillaume Richard, Arthur Flajolet, Thomas Pierrot, Antoine Cully
Journal of Machine Learning Research (JMLR) - MLOSS, 2024
(code)
(paper)
|
|
Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity
M. Allard, S. C. Smith, K. Chatzilygeroudis, Bryan Lim, A. Cully
ACM Transactions on Evolutionary Learning and Optimization (TELO), 2023
(arXiv)
|
|
Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning
M. Flageat*, Bryan Lim*, L. Grillotti, M. Allard, S. C. Smith, A. Cully
Quality Diversity Algorithm Benchmarks Workshop, GECCO, 2022
(arXiv)
|
Teaching
- C70050 Introduction to Machine Learning, TA
- C70028 Reinforcement Learning, TA
- C70067 Robot Learning and Control, TA
|
|