Learning complex manipulation tasks in realistic, obstructed environments is a challenging problem due to hard exploration in the presence of obstacles and high-dimensional visual observations. Prior work tackles the exploration problem by integrating motion planning and reinforcement learning. However, the motion planner augmented policy requires access to state information, which is often not available in the real-world settings. To this end, we propose to distill a state-based motion planner augmented policy to a visual control policy via (1) visual behavioral cloning to remove the motion planner dependency along with its jittery motion, and (2) vision-based reinforcement learning with the guidance of the smoothed trajectories from the behavioral cloning agent. We evaluate our method on three manipulation tasks in obstructed environments and compare it against various reinforcement learning and imitation learning baselines. The results demonstrate that our framework is highly sample-efficient and outperforms the state-of-the-art algorithms. Moreover, coupled with domain randomization, our policy is capable of zero-shot transfer to unseen environment settings with distractors. Code and videos are available at https://clvrai.com/mopa-pd
翻译:在现实、困难的环境中进行复杂的学习操作任务是一个具有挑战性的问题,原因是在存在障碍和高维视觉观测的情况下进行了艰苦的探索; 先前的工作通过整合运动规划和强化学习来解决勘探问题; 然而,动议规划者强化政策要求获取国家信息,而在现实世界环境中往往无法获得这些信息; 为此,我们提议通过下列方式将基于国家的运动规划者提升为视觉控制政策:(1) 视觉行为性克隆,以消除运动规划者的依赖性,同时消除其飞速运动;(2) 视觉强化学习,在行为性克隆剂平稳轨迹的指引下进行。 我们评估了在障碍环境中的三种操纵任务的方法,并将其与各种强化学习和模仿学习基线进行比较。 结果表明,我们的框架具有很高的样本效率,并超越了艺术状态的算法。 此外,除了域随机化外,我们的政策能够零发式地转移到转移器的看不见的环境环境中。 代码和视频可在https://clvrai.com/mopa-pd上查阅。