Profile cover photo
Profile photo
Massimiliano Patacchiola
122 followers -
#include<smartquotes.h>
#include<smartquotes.h>

122 followers
About
Massimiliano's interests
View all
Massimiliano's posts

Post has attachment
Dear friends! The fifth episode of the "Dissecting Reinforcement Learning" series is ready. In this post: Evolutionary Algorithms, Genetic Algorithms in Reinforcement Learning, Genetic Algorithms for policy selection. It includes Python code which can be reused in your personal project. The code is available on the GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Please share if you like...


Post has attachment
The fifth episode of the series is out there. Evolutionary and Genetic algorithms are introduced with intuitive examples and then I showed how they can be applied to Reinforcement Learning problems. As usual the Python code is available on the official GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Share if you like!

Post has attachment
The fifth episode of the series is out there. Evolutionary and Genetic algorithms are introduced with intuitive examples and then I showed how they can be applied to Reinforcement Learning problems. As usual the Python code is available on the official GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Share if you like!

Post has attachment
The fifth episode of the series is out there. Evolutionary and Genetic algorithms are introduced with intuitive examples and then I showed how they can be applied to Reinforcement Learning problems. As usual the Python code is available on the official GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Share if you like!

Post has attachment
Dear friends! The fifth episode of the "Dissecting Reinforcement Learning" series is ready. In this post: Evolutionary Algorithms, Genetic Algorithms in Reinforcement Learning, Genetic Algorithms for policy selection. It includes Python code which can be reused in your personal project. The code is available on the GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Please share if you like...

Post has attachment
An interesting post with useful resources on Deep Learning...

Post has attachment
This article introduce a paper that I have been studying in the last few days and that is related to my current research. Would be interesting to understand how a trust-based reinforcement mechanism can influence the cooperation strategy in a multi-agent system.

Post has attachment
The first Plymouth University NAO Hackathon has been a great success. As part of the organisation team I experienced the hackathon from a different point of view. All the organisers and the participants did a very good job! See you again in June...

Post has attachment
The fourth episode of the series "Dissecting Reinforcement Learning" is out there! In this episode I introduce Actor-Critic methods starting from a brief excursion in the neuroscience world. The complete Python code is available on my GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Please share if you like!

Post has attachment
The fourth episode of the series "Dissecting Reinforcement Learning" is out there! In this episode I introduce Actor-Critic methods starting from a brief excursion in the neuroscience world. The complete Python code is available on my GitHub repository:

https://github.com/mpatacchiola/dissecting-reinforcement-learning

Please share if you like!
Wait while more posts are being loaded