arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2004.13529cs.AI
收藏

基于观察的增强行为克隆

Augmented Behavioral Cloning from Observation

Pontifícia Universidade Católica do Rio Grande do Sul(南里奥格兰德天主教大学)

Juarez Monteiro, Nathan Gavenski, Roger Granada, Felipe Meneguzzi, Rodrigo Barros

摘要:

观察模仿是一种计算技术,它通过只观察来自专家演示的状态序列来教导代理如何模仿专家的行为。最近的方法学习环境的逆动力学和模仿政策,通过交错的时代,同时改变演示数据。然而,这种方法往往陷入远离专家的次优解决方案,限制了其模仿效果。我们用一种新的方法来解决这个问题,该方法通过探索:(I)一种自我注意力机制,可以更好地捕获状态的全局特征;(ii)一种采样策略,可以调节用于学习的观察结果。我们的经验表明,我们的方法优于国家的最先进的方法在四个不同的环境中的一个很大的利润。

英文摘要:

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of the environment and an imitation policy by interleaving epochs of both models while changing the demonstration data. However, such approaches often get stuck into sub-optimal solutions that are distant from the expert, limiting their imitation effectiveness. We address this problem with a novel approach that overcomes the problem of reaching bad local minima by exploring: (I) a self-attention mechanism that better captures global features of the states; and (ii) a sampling strategy that regulates the observations that are used for learning. We show empirically that our approach outperforms the state-of-the-art approaches in four different environments by a large margin.

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。

↑