M Kiran, M Ozyildirim - arXiv preprint arXiv:2201.11182, 2022 - arxiv.org
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 …
T Eimer, M Lindauer… - … Conference on Machine …, 2023 - proceedings.mlr.press
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 …