Seminario Datalab
RL reading group (3): Policy Gradients & PPO
Ponente: Pablo G. Arce (ICMAT-CSIC)Fecha: miércoles 09 de diciembre de 2026 - 12:00Online: https://tinyurl.com/ZoomRLRG
Resumen:
This Reinforcement Learning Reading Group at ICMAT-CSIC is a collaborative space aimed at both beginners and researchers. We will mainly draw on Kevin Murphy’s RL book, complemented with scientific papers and auxiliary materials for specific topics. Throughout the sessions, we will cover a wide range of topics, including Value-Based Methods, Deep Q-Learning, Policy Gradients, PPO, Multi-Agent RL, RL as Inference, and the intersection of LLMs & RL, among others. No prior expertise in RL is required to participate!
Mailing List: https://listas.csic.es/wws/subscribe/rl_reading_group?previous_action=edit_list_request (Non-Spanish speakers: click the “Suscribir” button)
Más información:
