Igor Machado de Castro

Sentinel-Augmented Reinforcement Learning with One-Step Ahead Predictive Safety Filtering

Reinforcement learning (RL) consists of a general trial-and-error learning structure in which an agent, based on observations, receives rewards or punishments according to the action taken. This approach has proven to be efficient in many fields of application, such as video game...

Sentinel-Augmented Reinforcement Learning with One-Step Ahead Predictive Safety Filtering

Reinforcement learning (RL) consists of a general trial-and-error learning structure in which an agent, based on observations, receives rewards or punishments according to the action taken. This approach has proven to be efficient in many fields of application, such as video game...