The expanding research on manifold-based self-supervised learning (SSL)
builds on the manifold hypothesis, which suggests that the inherent complexity
of high-dimensional data can be unraveled through lower-dimensional manifold
embeddings. Capitalizing on this, DeepInfomax with an unbalanced atlas (DIM-UA)
has emerged as a powerful tool and yielded impressive results for state
representations in reinforcement learning. Meanwhile, Maximum Manifold Capacity
Representation (MMCR) presents a new frontier for SSL by optimizing class
separability via manifold compression. However, MMCR demands extensive input
views, resulting in significant computational costs and protracted pre-training
durations. Bridging this gap, we present an innovative integration of MMCR into
existing SSL methods, incorporating a discerning regularization strategy that
enhances the lower bound of mutual information. We also propose a novel state
representation learning method extending DIM-UA, embedding a nuclear norm loss
to enforce manifold consistency robustly. On experimentation with the Atari
Annotated RAM Interface, our method improves DIM-UA significantly with the same
number of target encoding dimensions. The mean F1 score averaged over
categories is 78% compared to 75% of DIM-UA. There are also compelling gains
when implementing SimCLR and Barlow Twins. This supports our SSL innovation as
a paradigm shift, enabling more nuanced high-dimensional data representations.

通过引入 Maximum Manifold Capacity Representation 并与 DeepInfomax with an unbalanced atlas 相结合，本研究创新地整合了模型压缩的优化类别可分离性的方法，并通过核范数损失稳健地强制执行流形的一致性，从而在目标编码维度相同时显著提高了 DIM-UA 的性能。