Richard Liaw

Computer Science · Physical Sciences

14h-index1.9kcitations25works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(11), Machine Learning and Data Classification(6), Cloud Computing and Resource Management(5), Data Stream Mining Techniques(5), Parallel Computing and Optimization Techniques(4)

Publications25 total

SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent
arXiv (Cornell University)·2025Open Access
ESCHER
2022· 5 citedOpen Access
REVEAL 2022: Reinforcement Learning-Based Recommender Systems at Scale
2022
Elastic Hyperparameter Tuning on the Cloud
2021· 8 citedOpen Access
RubberBand
2021· 19 citedOpen Access
HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline
arXiv (Cornell University)·2020· 1 citedOpen Access
SWIRL: A SequentialWindowed Inverse Reinforcement Learning Algorithm for Robot Tasks With Delayed Rewards
Springer proceedings in advanced robotics·2020· 9 cited
IMPACT: Importance Weighted Asynchronous Architectures with Clipped Target Networks
arXiv (Cornell University)·2019· 1 citedOpen Access
IMPACT: Importance Weighted Asynchronous Architectures with Clipped\n Target Networks
arXiv (Cornell University)·2019· 8 citedOpen Access
HyperSched
2019· 42 citedOpen Access
Benchmarks for reinforcement learning in mixed-autonomy traffic
Conference on Robot Learning·2018· 77 cited
Large batch size training of neural networks with adversarial training and second-order information
arXiv (Cornell University)·2018· 35 citedOpen Access
SWIRL: A sequential windowed inverse reinforcement learning algorithm for robot tasks with delayed rewards
The International Journal of Robotics Research·2018· 62 cited
Tune: A Research Platform for Distributed Model Selection and Training
arXiv (Cornell University)·2018· 613 citedOpen Access
RLlib: Abstractions for Distributed Reinforcement Learning
International Conference on Machine Learning·2018· 191 cited
RLlib: Abstractions for Distributed Reinforcement Learning
arXiv (Cornell University)·2017· 328 citedOpen Access
Ray RLlib: A Framework for Distributed Reinforcement Learning
arXiv (Cornell University)·2017Open Access
Ray: A Distributed Framework for Emerging AI Applications
arXiv (Cornell University)·2017· 253 citedOpen Access
Ray RLLib: A Composable and Scalable Reinforcement Learning Library
arXiv (Cornell University)·2017· 109 citedOpen Access
Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
arXiv (Cornell University)·2017· 17 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Ion Stoica(16), Joseph E. Gonzalez(12), Eric Liang(9), Robert Nishihara(9), Philipp Moritz(9), Ken Goldberg(9), Michael I. Jordan(7), Alexey Tumanov(7), Roy Fox(5), Stephanie Wang(4), Sanjay Krishnan(4), Animesh Garg(4), Romil Bhardwaj(4), Lisa Dunlap(4), William Paul(3), Lauren Miller(3), Florian T. Pokorny(3), Brijen Thananjeyan(2), Johann Schleier-Smith(2), Mehrdad Niknami(2)