**Inverse Q-Learning (IQ-Learn)** is a a simple, stable & data-efficient framework for Imitation Learning (IL), that directly learns *soft Q-functions* from expert data. IQ-Learn enables **non-adverserial** imitation learning, working on both offline and online IL settings. It is performant even with very sparse expert data, and scales to complex image-based environments, surpassing prior methods by more than **3x**. 

It is very simple to implement requiring ~15 lines of code on top of existing RL methods.

<span class="description-source">Source: [IQ-Learn: Inverse soft Q-Learning for Imitation](https://arxiv.org/abs/2106.12142)</span>

**Attentive Normalization** generalizes the common affine transformation component in the vanilla feature normalization. Instead of learning a single affine transformation, AN learns a mixture of affine transformations and utilizes their weighted-sum as the final affine transformation applied to re-calibrate features in an instance-specific way. The weights are learned by leveraging feature attention.

Attentive Normalization

IQ-Learn

**OverFeat** is a classic type of convolutional neural network architecture, employing [convolution](https://paperswithcode.com/method/convolution), pooling and fully connected layers. The Figure to the right shows the architectural details.

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