Samuel Muñoz has been working as a research staff for the innovation department of BBVA Next Technologies for more than 3 years. Here he can fulfill his passion for artificial intelligence
and is always scouting the last trends and building disruptive prototypes. He likes to promote Free Software and knowledge sharing. You can find him in the library or outdoors, maybe
playing sports.
A gentle introduction to Reinforcement Learning and Inverse R.L.
11:30 - 12:00 Monday 21 September
This talk comes from our need to scout trends in Artificial Intelligence. We did not know anything about reinforcement learning and wanted to have our very own opinion on the topic to be able to decide if it could be a strategic working line in our roadmap. Inspired by AlphaZero we thought: “what else could be better than implementing a tic-tac-toe player with Q-learning?“ Moreover, we implemented the first part of the paper “Algorithms for Inverse RL” by Andrew NG and Stuart Russell to extract from the agent’s policy those positions that leaded to a victory.
Level: Medium
Language of speak: Inglés
Follow us