**A2C**, or **Advantage Actor Critic**, is a synchronous version of the [A3C](https://paperswithcode.com/method/a3c) policy gradient method. As an alternative to the asynchronous implementation of A3C, A2C is a synchronous, deterministic implementation that waits for each actor to finish its segment of experience before updating, averaging over all of the actors. This more effectively uses GPUs due to larger batch sizes.

Image Credit: [OpenAI Baselines](https://openai.com/blog/baselines-acktr-a2c/)

**DALL·E 2** is a generative text-to-image model made up of two main components: a prior that generates a CLIP image embedding given a text caption, and a decoder that generates an image conditioned on the image embedding.

DALL·E 2

Hierarchical Text-Conditional Image Generation with CLIP Latents

Asynchronous Methods for Deep Reinforcement Learning

**CoVe**, or **Contextualized Word Vectors**, uses a deep [LSTM](https://paperswithcode.com/method/lstm) encoder from an attentional sequence-to-sequence model trained for machine translation to contextualize word vectors. $\text{CoVe}$ word embeddings are therefore a function of the entire input sequence. These word embeddings can then be used in downstream tasks by concatenating them with $\text{GloVe}$ embeddings:

$$ v = \left[\text{GloVe}\left(x\right), \text{CoVe}\left(x\right)\right]$$

and then feeding these in as features for the task-specific models.

Source	Asynchronous Methods for Deep Reinforcement Learning
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com