Guilherme Peniche Cordeiro

Optimization of Code for Scalability of Deep Reinforcement Learning Agents in Slow and Stochastic Industrial Process Patterns

This work investigates the impact of code optimization techniques on the scalability and training time of deep reinforcement learning (DRL) agents applied to stochastic and slow-dynamic industrial process control environments. DRL combines deep learning and reinforcement learning to address high-dimensional decision-ma...