2019机器学习比赛_加速机器学习研究：在NeurIPS 2019与我们会面

2019机器学习比赛

In a few short weeks, Unity will be heading to NeurIPS in Vancouver (December 8–14). We’re sponsoring the main conference and the Women in Machine Learning (WiML) Workshop, as well as co-organizing the NeurIPS 2019 Workshop on Learning Transferable Skills. Learning transferable skills enable intelligent systems to generalize to new domains and tasks easily. This blog post explains why we’re eager to foster research in this area and provides an overview of the workshop we’re co-organizing. 

在短短的几周内，Unity将前往 温哥华的 NeurIPS (12月8日至14日)。 我们将赞助主要会议和 机器学习女性(WiML)研讨会 ，并共同组织NeurIPS 2019 学习可转移技能的研讨会 。 通过学习可转让的技能，智能系统可以轻松地推广到新的领域和任务。 这篇博客文章解释了为什么我们渴望促进这一领域的研究，并概述了我们正在共同组织的研讨会。

If you’re attending NeurIPS, consider joining our workshop on December 14. It will be packed with expert speakers presenting papers on generalization and learning-transferable skills. If you’re interested in exploring opportunities at Unity, drop by our booth (#324) in the Expo (December 8–11). You can also find us at the WiML Workshop (East Exhibition Hall C) on December 9.

如果您要参加NeurIPS，请考虑在12月14日加入我们的讲习班。该讲习班的讲演人员将介绍有关归纳和可学习技能的论文。 如果您有兴趣在Unity探索机会，请前往12月8日至11日在世博会我们的展位(＃324)。 您也可以 在12月9日 的WiML研讨会( 东展厅C ) 找到我们 。

关于转学的重要性 (On the importance of transfer learning)

After spending several decades on the margins of AI, reinforcement learning has recently emerged as a powerful framework for developing intelligent systems that can solve complex tasks in real-world environments – from playing games such as Dota and StarCraft to teaching a robot hand to manipulate a Rubik’s Cube. However, one attribute of intelligence that still eludes modern learning systems is generalizability. Until very recently, the majority of reinforcement learning research has involved training and testing algorithms in the same, often deterministic, environment. This has resulted in algorithms that learn policies that typically perform poorly when deployed in environments that differ even slightly from those in which they were trained. Even more importantly, the paradigm of task-specific training results in learning systems that scale poorly to a large number of tasks, even when the tasks are interrelated.

在AI边缘度过了几十年之后，强化学习最近成为一种强大的框架，可用于开发智能系统来解决现实环境中的复杂任务-从玩 Dota 和 StarCraft 等 游戏 到教机器人手 操纵 机器人。 魔方 。 但是，智能性仍然是现代学习系统无法理解的一个属性。 直到最近，大多数强化学习研究都在相同的，通常是确定性的环境中进行了训练和测试算法。 这导致算法学习策略的策略通常在部署于与受训策略甚至略有不同的环境中时表现通常很差。 更重要的是，任务特定训练的范式导致学习系统无法很好地扩展到大量任务，即使任务是相互关联的。

For instance, consider our work on learning to play Snoopy Pop from visual inputs using the Unity ML-Agents Toolkit. A game-playing agent that’s been trained on a specific number of levels may not perform well on a new, previously unseen level. Its performance might also begin to suffer if game mechanics are modified. This is problematic since games have become live services with ever-evolving content (e.g., new or changing levels, challenges, and missions). A game-playing agent would continuously need to be retrained to overcome this limitation, which could be time-consuming or prohibitively expensive. We are committed to developing learning systems that can easily generalize and adapt to new tasks or changing game mechanics to overcome this constraint. With the Unity ML-Agents Toolkit, we took the first step to addressing this challenge by providing the capability to train agents on distributions of tasks. 

例如，考虑一下我们 使用 Unity ML-Agents Toolkit 从视觉输入中 学习玩 Snoopy Pop的 工作 。 经过特定级别培训的游戏代理可能在以前看不见的新级别上表现不佳。 如果修改游戏机制，其性能也可能开始受到影响。 这是有问题的，因为游戏已经成为具有不断发展的内容(例如，新的或不断变化的关卡，挑战和任务)的实时服务。 游戏代理商必须不断地接受培训以克服这种限制，而这种限制可能是耗时的，也可能是昂贵的。 我们致力于开发可轻松推广并适应新任务或更改游戏机制以克服此限制的学习系统。 借助Unity ML-Agents工具包，我们迈出了第一步，通过提供对 代理进行任务分配培训 的能力来应对这一挑战 。

Fortunately, the machine learning research community has recently shown a reinvigorated interest in developing systems that can learn transferable skills. This could mean developing robustness to changing environment dynamics, the ability to quickly adapt to task variations, or a capacity to learn to perform multiple tasks at once (or any combination thereof). This interest has resulted in a number of new data sets and challenges, such as our own Obstacle Tower Environment and the Animal-AI Olympics (made with Unity and leveraging the Unity ML-Agents Toolkit). Both of these challenges demonstrate Unity’s strength as a powerful simulation platform for AI research. The NeurIPS 2019 Workshop on Learning Transferable Skills was organized to provide a forum to further accelerate research in this domain.

幸运的是，机器学习研究社区最近对开发可以学习可转让技能的系统重新产生了兴趣。 这可能意味着发展出对不断变化的环境动态的鲁棒性，快速适应任务变化的能力或学会一次执行多个任务的能力(或其任意组合)。 这种兴趣带来了许多新的数据集和挑战，例如我们自己的 障碍塔环境 和 Animal-AI奥林匹克运动会 (由Unity进行并利用Unity ML-Agents工具包)。 这两个挑战都证明了Unity作为AI研究强大的仿真平台的优势。 组织了NeurIPS 2019学习可转移技能研讨会，以提供一个论坛来进一步加速该领域的研究。

NeurIPS 2019研讨会概述 (NeurIPS 2019 workshop overview)

Interestingly, the first-ever workshop on the topic of transfer learning also took place at NeurIPS (then-called NIPS) in 1995. Back then, transfer learning was called Learning to Learn, an acknowledgment that a system’s ability to generalize to new tasks is a core tenant of learning. Since then, this research topic has been studied under many different names, such as life-long learning, knowledge transfer, multi-task learning, knowledge consolidation, meta-learning, and incremental/cumulative learning.

有趣的是， 有史以来第一次关于迁移学习的研讨会 也于1995年在NeurIPS(当时称为NIPS)上举行。当时，迁移学习称为“学习学习”，它承认系统具有将新的任务概括为新功能的能力。学习的核心租户。 从那时起，这个研究主题就以许多不同的名称进行了研究，例如终身学习，知识转移，多任务学习，知识整合，元学习和增量/累积学习。

Twenty-four years after that first workshop, we’re excited to co-organize the Workshop on Learning Transferable Skills with Benjamin Crosby and Ben Beyret (from Imperial College London and the organizers of the Animal-AI Olympics). The workshop will include a full day of presentations by invited speakers and authors of peer-reviewed papers. Our invited speakers include ​David Ha (Google Brain), Raia Hadsell (DeepMind), Vladlen Koltun (Intel), Katja Hofmann (Microsoft Research), ​Wojciech Zaremba (OpenAI), Karl Cobbe (OpenAI), and Gianni De Fabritiis (University Pompeu Fabra), whose presentations will cover aspects of transfer learning for computer vision, robotics and games.

在首次研讨会之后的二十四年，我们很高兴 与本杰明·克罗斯比和本·贝雷特(来自伦敦帝国学院和动物AI奥林匹克运动会的组织者) 共同组织了 学习可转移技能 的 研讨会 。 研讨会将包括由受邀演讲者和同行评审论文的作者作一整天的演讲。 我们的受邀演讲者包括David Ha(Google Brain)，Raia Hadsell(DeepMind)，Vladlen Koltun(Intel)，Katja Hofmann(Microsoft Research)，Wojciech Zaremba(OpenAI)，Karl Cobbe(OpenAI)和Gianni De Fabritiis(大学Pompeu Fabra，其演讲将涵盖计算机视觉，机器人技术和游戏的迁移学习的各个方面。

—

-

If you are attending NeurIPS, join us to learn more about how to develop learning systems able to generalize to new tasks and domains.

如果您要参加NeurIPS，请加入我们以了解更多有关如何开发能够推广到新任务和领域的学习系统的信息。

翻译自: https://blogs.unity3d.com/2019/11/29/accelerating-ml-research-meet-us-at-neurips-2019/

2019机器学习比赛