Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
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…
cs.LG2024
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…