riccardodesanti

Riccardo De Santi's starred repositories

100 exercises to learn JAX

Language:Jupyter NotebookApache-2.055700

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Language:PythonMIT114700

Implementation of the MEPOL algorithm - A policy gradient method for task-agnostic exploration

Language:Python1300

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

Language:Jupyter Notebook6200

Hands-on Deep Reinforcement Learning, published by Packt

Language:PythonMIT278600

Summary of the "Discrete Mathematics" course at ETH Zürich

Language:TeX300