The paper introduces Rollback, a method that uses action‑conditioned world models to backtrack to critical decision points, branch into alternative actions, and compare outcomes to attribute success to individual decisions. By turning world models into counterfactual engines, Rollback provides fine‑grained, action‑level supervision without a separate value model and integrates distributed world‑model search with asynchronous real‑robot execution. Experiments on block extraction, ball tossing, and tabletop curling show that Rollback improves success rates by over 10% compared to the strongest baseline and surpasses human performance on two tasks within eight hours of training.
By Jiayi Luo, Yang Zhang, Liliang Chen, Nan Wang, Chen Gao, Boxiang Qiu, Zhuoxuan Li, Baorui Peng, Chuankang Li, Yuxiang Yan, Si Liu, Qingyun Sun, Shuicheng Yan, Maoqing Yao, Jianxin Li, Guanghui Ren
arXiv:2607. 02431v1 Announce Type: cross Abstract: 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.
By Yuquan Xue, Le Xu, Zeyi Liu, Zhenyu Wu, Zhengyi Gu, Xinyang Song, Bofang Jia, Ziwei Wang
arXiv:2602. 13977v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to unlock capabilities beyond imitation learning for Vision--Language--Action (VLA) models, but its requirement for massive real-world interaction prevents direct deployment on physical robots.
By Zhennan Jiang, Shangqing Zhou, Yutong Jiang, Zefang Huang, Mingjie Wei, Yuhui Chen, Tianxing Zhou, Zhen Guo, Hao Lin, Quanlu Zhang, Yu Wang, Haoran Li, Chao Yu, Dongbin Zhao
arXiv:2608.24885v1 Announce Type: cross
Abstract: Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on a...
By Sixiang Chen, Jiaming Liu, Jixian Wu, Yichen Guo, Tinghao Wang, Siyuan Qian, Hao Chen, Jiajun Cao, Jian Tang, Shanghang Zhang
Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithful...
RoboCoach introduces a world-model-guided coaching framework that uses imagined failures to direct demonstration requests and expert updates for robot manipulation tasks. The system, called RIDI, runs reusable skill experts within a shared action-conditioned world model and records the first failing subtask to decide which demonstrations to acquire and which adapters to refine. Experiments on simulation suites and real robots show that with only 150 additional subtask demonstrations, success rates increase dramatically, and the coached experts transfer effectively to unseen task compositions.
By Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang
arXiv:2607. 15065v1 Announce Type: cross Abstract: Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly.
By Susie Lu, Haonan Chen, Weirui Ye, Yilun Du
arXiv:2610.35604v1 Announce Type: cross
Abstract: Generalist robot policies and language-model agents provide complementary capabilities, but completing a task also requires adapting their use to the...
By Heyang Yu, Haomin Li, Sihang Li, Jixin Yan, Shiyun Peng, Wanqi Zhong, Tianyu Xin, Yuan Yao, Xiaoyu Tian, Yiming Li
arXiv:2610.40565v1 Announce Type: cross
Abstract: Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decade...
By Pranjal Aggarwal, Sean Welleck
arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.
By Raymond Yu, William Huey, Mustafa Mukadam, Anusha Nagabandi, Abhishek Gupta
The paper introduces a feedback world model that updates predictions online using the robot’s observed next state after each action, thereby closing the loop between prediction and observation. This lightweight feedback state corrects future predictions without extra training or parameter updates, and the authors provide convergence guarantees under bounded dynamics residuals. Experiments on LIBERO‑Plus, Robomimic, and real‑world tasks show significant reductions in prediction error (up to 76.4%) and improved policy performance, even when applied to pretrained foundation models like Fast‑WAM‑Joint.
By Tuo An, Jindou Jia, Gen Li, Jingliang Li, Chuhao Zhou, Pengfei Liu, Bofan Lyu, Jiaqi Bai, Xinying Guo, Geng Li, Jianfei Yang
The paper introduces a reinforcement learning post‑training scheme that trains robot world models on their own autoregressive rollouts, using a contrastive RL objective adapted from diffusion models. It also proposes a training protocol that compares multiple variable‑length futures, a multi‑view visual fidelity reward, and demonstrates state‑of‑the‑art rollout fidelity on the DROID dataset, outperforming baselines on LPIPS, SSIM, and human preference tests.
By Jai Bardhan, Patrik Drozdik, Josef Sivic, Vladimir Petrik