**FORK**, or **Forward Looking Actor** is a type of actor for actor-critic algorithms. In particular, FORK includes a neural network that forecasts the next state given the current state and current action, called system network; and a neural network that forecasts the
reward given a (state, action) pair, called reward network. With the system network and reward network, FORK can forecast the next state and consider the value of the next state when improving the policy.

**Deflation** is a video-to-image operation to transform a video network into a network that can ingest a single image. In the two types of video networks considered in the original paper, this deflation corresponds to the following operations: for [3D convolutional based networks](https://paperswithcode.com/method/3d-convolution), summing the 3D spatio-temporal filters over the temporal dimension to obtain 2D filters; for TSM networks,, turning off the channel shifting which results in a standard [residual architecture](https://paperswithcode.com/method/resnet) (ResNet50) for images.

Deflation

Self-Supervised MultiModal Versatile Networks

FORK

FORK: A Forward-Looking Actor For Model-Free Reinforcement Learning

**Kaiming Initialization**, or **He Initialization**, is an initialization method for neural networks that takes into account the non-linearity of activation functions, such as [ReLU](https://paperswithcode.com/method/relu) activations.

A proper initialization method should avoid reducing or magnifying the magnitudes of input signals exponentially. Using a derivation they work out that the condition to stop this happening is:

$$\frac{1}{2}n\_{l}\text{Var}\left[w\_{l}\right] = 1 $$

This implies an initialization scheme of:

$$ w\_{l} \sim \mathcal{N}\left(0,  2/n\_{l}\right)$$

That is, a zero-centered Gaussian with standard deviation of $\sqrt{2/{n}\_{l}}$ (variance shown in equation above). Biases are initialized at $0$.

Source	FORK: A Forward-Looking Actor For Model-Free Reinforcement Learning
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com