Category Archive: Tecnology

Prioritized Experience Replay

Research project: Reinforcement Learning Actor-Critic Deep-Q Recurrent Networks for timeseries prediction How to achieve better performance and faster training using Prioritized Experience Replay? From DeepMind original paper: Prioritized Experience Replay Experience replay lets our reinforcement learning agent collect, remember and reuse experiences from the past. These experience transitions were usually uniformly sampled from a replay…

Read more
0 675


A CFO ask his CEO: “What could happen if we were to invest in the development of our people and then they would leave us?” The CEO answers: “What could happen if week end don’t invest and these, then, stay with us?” Certifications paths Nature and the world around us show that evolution and growth…

Read more

Reinforcement learning

Our research project in the field of Reinforcement learning: Actor-critic Deep-Q recurrent networks for temporal sequencing Project description: Starting from developing new techniques of time series analysis, through the use of virtual environments for the training of model-free agents, we want to generate an actor/critic agent (Barto et al.1988) that optimizes and surpasses the performances…

Read more