Talk at the Industrial RL Workshop in Saclay about the lessons learned while developping Stable-Baselines3 to have reliable implementations and reproducible experiments.
In search of the simplest baseline capable of competing with Deep Reinforcement Learning on locomotion tasks, we propose a biologically inspired model-free open-loop strategy. Drawing upon prior knowledge and harnessing the elegance of simple …
Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design. Whereas previous works have focused on extensive modeling and simulation to find optimal controllers for …
Proximal policy optimization (PPO) has become one of the most popular deep reinforcement learning (DRL) algorithms. Yet, reproducing the PPO's results has been challenging in the community. While recent works conducted ablation studies to provide …
Stable-Baselines3 provides open-source implementations of deep reinforcement learning (RL) algorithms in Python. The implementations have been benchmarked against reference codebases, and automated unit tests cover 95% of the code. The algorithms …
We extend the original state-dependent exploration (SDE) to apply deep reinforcement learning algorithms directly on real robots. The resulting method, gSDE, yields competitive results in simulation but outperforms the unstructured exploration on the real robot.