WorldSample: Closed-loop Real-robot RL with World Modelling
Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorYuquan Xue →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorLe Xu →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorZeyi Liu →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorZhenyu Wu →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorZhengyi Gu →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorXinyang Song →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorBofang Jia →
WorldSample: Closed-loop Real-robot RL with World Modelling
- Linked via arxiv authorZiwei Wang →
WorldSample: Closed-loop Real-robot RL with World Modelling