Simulation provides a low-cost sandbox where embodied agents can attempt tasks, observe outcomes, and learn from experience. Running many diverse simulation environments concurrently can consume substantial CPU and GPU memory because independently constructed scenes duplicate resources that remain unchanged across inst...
Zi-Xu Hao, Wei-Jun Wang, Xiangyu Li et al.· 0 citations
Embodied reinforcement learning (RL) improves model capabilities with a pipeline of environment simulation, action generation, and model updates. These stages show heterogeneous CPU and GPU demands, making efficient resource utilization difficult. Recent systems overlap rollout (simulation and generation) with training...
Zetta is presented, a closed-loop embodied harness that evolves code-based runtime critics and recovery skills online while keeping the base policy frozen, and shows that closed-loop harness self-evolution opens a scaling path for reliable physical intelligence.