arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02066cs.LGcs.AIcs.ROstat.ML
收藏

跟随目标:具有想象目标的操作任务的课程学习

Follow the Object: Curriculum Learning for Manipulation Tasks with Imagined Goals

WMG;University of Warwick(华威大学)

Ozsel Kilinc, Giovanni Montana

摘要:

在具有稀疏奖励的环境中通过深度强化学习来学习机器人操作是一项具有挑战性的任务。在本文中,我们解决这个问题,通过引入一个概念的假想对象的目标。对于给定的操纵任务,首先通过物理逼真的模拟来训练感兴趣的对象,使其在不被操纵的情况下自行到达期望的目标位置。然后,利用对象策略来构建合理对象轨迹的预测模型,为机器人提供在训练期间要达到的越来越困难的对象目标的课程。所提出的算法,跟随对象(FO),已评估7 MuJoCo环境需要增加程度的探索,并取得了更高的成功率相比,替代算法。在特别具有挑战性的学习场景中,例如,对象的初始位置和目标位置相距甚远,我们的方法仍然可以学习策略,而竞争方法目前失败了。

英文摘要:

Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task. In this paper we address this problem by introducing a notion of imaginary object goals. For a given manipulation task, the object of interest is first trained to reach a desired target position on its own, without being manipulated, through physically realistic simulations. The object policy is then leveraged to build a predictive model of plausible object trajectories providing the robot with a curriculum of incrementally more difficult object goals to reach during training. The proposed algorithm, Follow the Object (FO), has been evaluated on 7 MuJoCo environments requiring increasing degree of exploration, and has achieved higher success rates compared to alternative algorithms. In particularly challenging learning scenarios, e.g. where the object's initial and target positions are far apart, our approach can still learn a policy whereas competing methods currently fail.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑