4 papers
Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
Sid Bharthulwar, Stone Tao, Hao Su
Massively parallel GPU simulation environments have accelerated reinforcement learning (RL) research by enabling fast data collection for on-policy RL algorithms like Proximal Poli…
ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
Arth Shukla, Stone Tao, Hao Su
High-quality benchmarks are the foundation for embodied AI research, enabling significant advancements in long-horizon navigation, manipulation and rearrangement tasks. However, as…
Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning
Stone Tao, Arth Shukla, Tse-kai Chan +1
Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve c…
AdaDemo: Data-Efficient Demonstration Expansion for Generalist Robotic Agent
Tongzhou Mu, Yijie Guo, Jie Xu +4
Encouraged by the remarkable achievements of language and vision foundation models, developing generalist robotic agents through imitation learning, using large demonstration datas…