Теория

Real Pendulum: обучи своего DIY робота с помощью RL

Controlling Overestimation Bias  with Truncated Mixture of Continuous Distributional Quantile Critics (ICML 2020)

Off-policy Evaluation with GradientDICE

RL in Industrial Robotics

RL for the adaptive speed regulation on a metallurgical pickling line

SampleFactory and high-throughput reinforcement learning

Reinforcement Learning in a Nutshell. Games, articles, production - choose wisely.

Главное Data Science событие года в онлайн формате!
Присоединяйся, чтобы получить доступ к паролю от нетворкинг комнат в SpatialChat и трекам с контентом от организаторов.

Reinforcement Learning

Track program

Real Pendulum: обучи своего DIY робота с помощью RL

Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics (ICML 2020)

Off-policy Evaluation with GradientDICE

RL in Industrial Robotics

RL for the adaptive speed regulation on a metallurgical pickling line

SampleFactory and high-throughput reinforcement learning

Related Tracks

Catalyst and Reinforcement Learning