2022

Prompts and Pre-Trained Language Models for Offline Reinforcement Learning

Prompt engineering can be successfully used for deep offline reinforcement learning in environments that are not naturally suited for the textual representation.

Forbes 30 under 30

Tinkoff Lab. RL Event

--

Animus

Minimalistic framework to run machine learning experiments.

Self Supervised Time Management [RU]

Time Management practices.

Probabilistic Embeddings Revisited

In recent years, deep metric learning and its probabilistic extensions achieved state-of-the-art results in a face verification task. However, despite improvements in face verification, probabilistic methods received little attention in the …

Tinkoff Lab. NLP Event

--

Animus

Minimalistic framework to run machine learning experiments

South Africa. Nomad Edition.

Month-long digital nomad trip to SA.

Южная Африка: лучше поздно, чем никогда [RU]

Один месяц в ЮАР - как это было.