Contemporary artificial intelligence systems exhibit rapidly growing
abilities accompanied by the growth of required resources, expansive datasets
and corresponding investments into computing infrastructure. Although earlier
successes predominantly focus on constrained settings, recent strides in
fundamental research and applications aspire to create increasingly general
systems. This evolving landscape presents a dual panorama of opportunities and
challenges in refining the generalisation and transfer of knowledge - the
extraction from existing sources and adaptation as a comprehensive foundation
for tackling new problems. Within the domain of reinforcement learning (RL),
the representation of knowledge manifests through various modalities, including
dynamics and reward models, value functions, policies, and the original data.
This taxonomy systematically targets these modalities and frames its discussion
based on their inherent properties and alignment with different objectives and
mechanisms for transfer. Where possible, we aim to provide coarse guidance
delineating approaches which address requirements such as limiting environment
interactions, maximising computational efficiency, and enhancing generalisation
across varying axes of change. Finally, we analyse reasons contributing to the
prevalence or scarcity of specific forms of transfer, the inherent potential
behind pushing these frontiers, and underscore the significance of
transitioning from designed to learned transfer.

当代人工智能系统的不断发展需要相应的资源、大量数据集和计算基础设施，特别是在限制环境下的基础研究和应用中，知识的表示通过各种模态呈现，包括动力学和奖励模型、价值函数、策略和原始数据。该论文系统地讨论了这些模态，并基于其固有属性和与不同目标和机制之间的相互关系来进行讨论，以实现知识的迁移和推广，并分析了特定形式的转移出现或稀缺的原因，并强调从设计到学习的转移的重要性。

强化学习中的迁移基础：知识模式分类

Foundations for Transfer in Reinforcement Learning: A Taxonomy of  Knowledge Modalities

High Performance Computing (HPC), Artificial Intelligence (AI)/Machine
Learning (ML), and Quantum Computing (QC) and communications offer immense
opportunities for innovation and impact on society. Researchers in these areas
depend on access to computing infrastructure, but these resources are in short
supply and are typically siloed in support of their research communities,
making it more difficult to pursue convergent and interdisciplinary research.
Such research increasingly depends on complex workflows that require different
resources for each stage. This paper argues that a more-holistic approach to
computing infrastructure, one that recognizes both the convergence of some
capabilities and the complementary capabilities from new computing approaches,
be it commercial cloud to Quantum Computing, is needed to support computer
science research.

本文主要探讨了高性能计算、人工智能 / 机器学习和量子计算以及通信对于计算机科学研究领域的创新和影响，并指出在支持计算机科学研究方面需要更全面的计算基础设施，包括商业云计算和量子计算等新的计算方法。