计算机科学
人工智能
机器人学
强化学习
任务(项目管理)
一套
领域(数学分析)
编码(内存)
计算机视觉
学习迁移
机器人
任务分析
机器学习
培训(气象学)
可视化
传输(计算)
工作(物理)
机械臂
视觉控制
视觉学习
机器视觉
深度学习
训练集
人机交互
作者
Abdulaziz Almuzairee,Henrik I. Christensen
标识
DOI:10.1109/lra.2026.3730387
摘要
Visual reinforcement learning is appealing for robotics but expensive. Off-policy methods are sample-efficient yet slow while on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster than on-policy methods in wall-clock time for state-based control. Extending this to vision remains challenging, where high-dimensional input images complicate training dynamics and introduce substantial storage and encoding overhead. To address these challenges, we introduce Squint, a visual Soft Actor Critic method that achieves faster wall-clock training than prior visual off-policy and on-policy methods. Squint achieves this via parallel simulation, a distributional critic, resolution squinting, layer normalization, a tuned update-to-data ratio, and an optimized implementation. We evaluate on the SO-101 Task Set, a new suite of eight manipulation tasks in ManiSkill3 with heavy domain randomization, and demonstrate sim-to-real transfer to a real SO-101 robot. We train policies for 15 minutes on a single RTX 3090 GPU, with most tasks converging in under 6 minutes.
科研通智能强力驱动
Strongly Powered by AbleSci AI