3 papers
cs.LG2026
Learning More from Less: Reinforcement Learning from Hindsight
Iris Xu, Sunshine Jiang, John Marangola +8
Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, but every update consumes robot rollouts that are slow and costly to collect, ma…
cs.LG2026
Prompt-Driven Exploration
Sunshine Jiang, John Marangola, David Zhang +6
Exploration is essential to RL since a policy cannot improve by repeatedly sampling the behaviors it already prefers. Standard methods inject stochasticity in the action space, but…
cs.LG2025
ViVa: Video-Trained Value Functions for Guiding Online RL from Diverse Data
Nitish Dashora, Dibya Ghosh, Sergey Levine
Online reinforcement learning (RL) with sparse rewards poses a challenge partly because of the lack of feedback on states leading to the goal. Furthermore, expert offline data with…