In a **Replacing Eligibility Trace**, each time the state is revisited, the trace is reset to $1$ regardless of the presence of a prior trace.. For the memory vector $\textbf{e}\_{t} \in \mathbb{R}^{b} \geq \textbf{0}$:

$$\mathbf{e\_{0}} = \textbf{0}$$

$$\textbf{e}\_{t} = \gamma\lambda{e}\_{t-1}\left(s\right) \text{ if } s \neq s\_{t}$$

$$\textbf{e}\_{t} = 1 \text{ if } s = s\_{t}$$

They can be seen as crude approximation to dutch traces, which have largely superseded them as they perform better than replacing traces and have a clearer theoretical basis. Accumulating traces remain of interest for nonlinear function approximations where dutch traces are not available.

Source: Sutton and Barto, Reinforcement Learning, 2nd Edition

**BlendMask** is an [instance segmentation framework](https://paperswithcode.com/methods/category/instance-segmentation-models) built on top of the[ FCOS](https://paperswithcode.com/method/fcos) object detector. The bottom module uses either backbone or [FPN](https://paperswithcode.com/method/fpn) features to predict a set of bases. A single [convolution](https://paperswithcode.com/methods/category/convolutions) layer is added on top of the detection towers to produce attention masks along with each bounding box prediction. For each predicted instance, the [blender](https://paperswithcode.com/method/blender) crops the bases with its bounding box and linearly combine them according the learned attention maps. Note that the Bottom Module can take features either from ‘C’, or ‘P’ as the input.

BlendMask

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

Replacing Eligibility Trace

**mt5** is a multilingual variant of [T5](https://paperswithcode.com/method/t5) that was pre-trained on a new Common Crawl-based dataset covering $101$ languages.

Year	2000
Data Source	CC BY-SA - https://paperswithcode.com