We present a system for learning a challenging dexterous manipulation task involving moving a cube to an arbitrary 6-DoF pose with only 3-fingers trained with NVIDIA's IsaacGym simulator. We show empirical benefits, both in simulation and sim-to-real transfer, of using keypoints as opposed to position+quaternion representations for the object pose in 6-DoF for policy observations and in reward calculation to train a model-free reinforcement learning agent. By utilizing domain randomization strategies along with the keypoint representation of the pose of the manipulated object, we achieve a high success rate of 83% on a remote TriFinger system maintained by the organizers of the Real Robot Challenge. With the aim of assisting further research in learning in-hand manipulation, we make the codebase of our system, along with trained checkpoints that come with billions of steps of experience available, at https://s2r2-ig.github.io

翻译：我们提出了一个系统,用于学习具有挑战性的极具挑战性的操纵任务,即将一个立方体变成一个任意的6-DoF的外形,只有3个受NVIIDAA的IsaacGym模拟器培训的3个侧翼人。我们展示了模拟和模拟到真实转移方面的经验性好处,即在6-DoF中使用关键点而不是定位+方位表示器,作为政策观察和奖励计算,以训练一个无模型的强化学习剂。我们利用域随机化战略以及被操纵物体的外形关键代表,在由实生机器人挑战组织者维护的远程三角方格系统中取得了高达83%的成功率。为了协助进一步研究手动操作的学习,我们在https://s2-rig.githubio上建立了我们的系统代码库,以及经过培训、经验达数十亿步的检查站,可在https://s2-rig.github.