Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Learning with a Single Rollout via Pass@k Policy Optimization
Fengdi Che, Yang Liu, Lei Yu +4
Group Relative Policy Optimization (GRPO) typically requires multiple rollouts per prompt to estimate relative credit, incurring substantial sampling cost and exacerbating training…
cs.LG2021
Model-free Policy Learning with Reward Gradients
Qingfeng Lan, Samuele Tosatto, Homayoon Farrahi +1
Despite the increasing popularity of policy gradient methods, they are yet to be widely utilized in sample-scarce applications, such as robotics. The sample efficiency could be imp…