Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning

no code implementations • 1 Jun 2024 • Andrej Orsula

In the context of addressing the Robot Air Hockey Challenge 2023, we investigate the applicability of model-based deep reinforcement learning to acquire a policy capable of autonomously playing air hockey.

Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space

1 code implementation • 2 May 2024 • Andrej Orsula, Matthieu Geist, Miguel Olivares-Mendez, Carol Martinez

We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space.

reinforcement-learning

Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning

1 code implementation • 1 Aug 2022 • Andrej Orsula, Simon Bøgh, Miguel Olivares-Mendez, Carol Martinez

Domain randomization improves the generalization of learned policies to novel scenes with previously unseen objects and different illumination conditions.

Reinforcement Learning (RL) Robotic Grasping