arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.04388cs.LGcs.AIcs.ROstat.ML
收藏

GRIMGEP:视觉深度强化学习中鲁棒目标采样的学习进展

GRIMGEP: Learning Progress for Robust Goal Sampling in Visual Deep Reinforcement Learning

Grgur Kovač, Adrien Laversanne-Finot, Pierre-Yves Oudeyer

摘要:

为了扩大强化学习的范围,设计能够自主学习各种技能的代理是至关重要的。它将增加学习技能的多样性,并减少为每个技能手动设计奖励功能的负担。自我监督的代理人,设定自己的目标,并试图最大限度地提高这些目标的多样性,已经显示出很大的希望实现这一目标。然而,目前已知的代理试图最大化采样目标的多样性的限制是,他们往往会被吸引到噪音或更一般的环境中的部分,不能控制(干扰)。当智能体可以访问预定义的目标特征或专家知识时,绝对学习进度(ALP)提供了一种区分可以控制的区域和不能控制的区域的方法。然而,当代理仅被提供原始感觉输入(例如图像)时,这些方法常常不足。在这项工作中,我们将这些概念扩展到无监督的基于图像的目标探索。我们提出了一个框架,允许代理自主识别和忽略嘈杂的分心区域,同时在可学习区域中搜索新颖性,以提高整体性能并避免灾难性遗忘。我们的框架可以与任何最先进的新奇寻求目标探索方法相结合。我们构建了一个丰富的三维图像为基础的环境与干扰。在这个环境中的实验表明,代理使用我们的框架成功地识别出有趣的区域的环境,从而大大提高了性能。源代码可在https://sites.google.com/view/grimgep上获得。

英文摘要:

Designing agents, capable of learning autonomously a wide range of skills is critical in order to increase the scope of reinforcement learning. It will both increase the diversity of learned skills and reduce the burden of manually designing reward functions for each skill. Self-supervised agents, setting their own goals, and trying to maximize the diversity of those goals have shown great promise towards this end. However, a currently known limitation of agents trying to maximize the diversity of sampled goals is that they tend to get attracted to noise or more generally to parts of the environments that cannot be controlled (distractors). When agents have access to predefined goal features or expert knowledge, absolute Learning Progress (ALP) provides a way to distinguish between regions that can be controlled and those that cannot. However, those methods often fall short when the agents are only provided with raw sensory inputs such as images. In this work we extend those concepts to unsupervised image-based goal exploration. We propose a framework that allows agents to autonomously identify and ignore noisy distracting regions while searching for novelty in the learnable regions to both improve overall performance and avoid catastrophic forgetting. Our framework can be combined with any state-of-the-art novelty seeking goal exploration approaches. We construct a rich 3D image based environment with distractors. Experiments on this environment show that agents using our framework successfully identify interesting regions of the environment, resulting in drastically improved performances. The source code is available at https://sites.google.com/view/grimgep.

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。

↑