A data-driven approach to analyzing athletics peak performance

My passion for running and track and field has always tried to accompany me during the different phases of my life. I used to run for fun when I was a child and to compete in school races during my high-school years. It was only during my college years that running took a pause from my life while my curiosity about data science progressively took … Continue reading A data-driven approach to analyzing athletics peak performance

Train hard and recover harder: why you should take a recovery week

You might believe that the optimal strategy for training for a marathon or other target race is to hit your peak mileage and maintain it for several weeks. By doing this, you’ll make sure to get the most out of your fitness and prepare well for your target race, right? Maybe not. It may have happened that after a period of heavy training load you … Continue reading Train hard and recover harder: why you should take a recovery week

Challenging the memory of RL agents

Reinforcement learning agents are usually trained to maximize their rewards by taking actions in an environment following a Markov Decision Process (MDP). A Markov Decision Process is simply a model that defines the state of an environment by its current state, actions, and rewards, including also its possible future states. The key point is that agents know information from the present and can approximately predict … Continue reading Challenging the memory of RL agents

Exploring Transformer Model for Reinforcement Learning

MLP is widely used in RL to implement a learnable agent in a certain environment trained according to a specific algorithm. Recent works in NLP have already proved that Transformer can replace and outperform MLP in most tasks leading to expanding its utilization in areas outside of NLP such as Computer Vision. However, in RL the Transformer architecture is still not widely adopted, and agents … Continue reading Exploring Transformer Model for Reinforcement Learning