Reinforcement Learning

A presentation on the current challenges of RL (RL is hard, implementation details) and trying to make RL work out of the box (reducing complexity, SAC on IsaacSim, automatic hyperparameter optimization).

This tutorial covers direct policy search methods for RL, including black-box optimization (BBO), finite-differences and policy gradient (PG) approaches.

From Tabular Q-learning to Deep Q-Network (DQN)

An overview of exploration methods for continuous control RL, covering exploration in parameter space, action space, state-dependent exploration (gSDE), and guided exploration.

A presentation on recent advances in model free RL (SOTA early 2026), in terms of algorithms, software, and simulators.

This tutorial will present the basics of the Gymnasium and Stable-Baselines3 (SB3) libraries in order to apply reinforcement learning in practice. The session will cover the basics of how to create a custom task and solve it using algorithms from …

This dissertation makes several contributions to the training of reinforcement learning agents directly on real robots. It introduces a reliable software suite and a new exploration strategy to replace the standard step-based one. The thesis also …

A presentation on recent advances in RL, in terms of algorithms, software, and simulators.

Invited talk while visiting the INRIA Willow team in Paris.

Invited talk for the Soccer Robots workshop at Humanoids conference 2024