Neural networks dominate the modern machine learning landscape, but their training and
success still suffer from sensitivity to empirical choices of hyperparameters such as model …

Reinforcement learning (RL) applications, where an agent can simply learn optimal
behaviors by interacting with the environment, are quickly gaining tremendous success in a …

Reinforcement learning (RL) offers the potential for training generally capable agents that
can interact autonomously in the real world. However, one key limitation is the brittleness of …

Recently, the development of neural machine translation (NMT) has significantly improved
the translation quality of automatic machine translation. While most sentences are more …

Despite significant progress in challenging problems across various domains, applying state-
of-the-art deep reinforcement learning (RL) algorithms remains challenging due to their …

In order to improve reproducibility, deep reinforcement learning (RL) has been adopting
better scientific practices such as standardized evaluation metrics and reporting. However …

In spite of the recent success of neural machine translation (NMT) in standard benchmarks,
the lack of large parallel corpora poses a major practical problem for many language pairs …

We describe Sockeye (version 1.12), an open-source sequence-to-sequence toolkit for
Neural Machine Translation (NMT). Sockeye is a production-ready framework for training …

We propose minimum risk training for end-to-end neural machine translation. Unlike
conventional maximum likelihood estimation, minimum risk training is capable of optimizing …

In this paper, we study a new learning paradigm for neural machine translation (NMT).
Instead of maximizing the likelihood of the human translation as in previous works, we …