Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning (RL) due to its clear mathematical definition and easy interpretability. Traditional methods directly restrict the total return variance. Recent methods restrict the per-step reward variance as a proxy.

This paper describes RETV ec, an efficient, resilient, and multilingual text vec-torizer designed for neural-based text processing. RETV ec combines a novel character encoding with an optional small embedding model to embed words into a 256-dimensional vector space. The RETV ec embedding model is pre-trained using pair-wise metric learning to be robust against typos and character-level adversarial attacks. In this paper, we evaluate and compare RETV ec to state-of-the-art vectorizers and word embeddings on popular model architectures and datasets. These comparisons demonstrate that RETV ec leads to competitive, multilingual models that are significantly more resilient to typos and adversarial text attacks.

Recent advances in machine learning and artificial intelligence have relied on fitting highly overparam-eterized models, notably deep neural networks, to observed data; e.g.

The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind.