Q: Do I need experience with real robots to participate in this challenge?
A: Real robot experience is not required. The challenge is specifically designed for machine learning practitioners.
Q: Can I access the evaluation simulator?
A: The evaluation simulator cannot be accessed by the participant of the challenge. The participants are allowed to access a limited amount of data daily from the simulator. All the rest of the code is available.
Q: Can I use standard robotics solutions for this challenge?
A: While it is possible to design the system with classical robotics solutions, we require that the proposed method employs machine learning techniques. These techniques are also important to deal with the sim-to-real gap.
Q: What types of machine learning algorithms can be used to solve this challenge?
A: All types of machine learning approaches are allowed. Relevant approaches include, but are not limited to, reinforcement learning, supervised learning, adaptive control, sim-to-real approaches, and bayesian optimization.
Q: Is there any relevant publication on how to structure an Air Hockey agent?
A: The literature on Air Hockey is quite rich. We can suggest two papers from wich the baselines and the environments have been build:
Liu, P., Tateo, D., Bou-Ammar, H., & Peters, J. (2021, September). Efficient and reactive planning for high speed robot air hockey. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 586-593). IEEE.
Liu, P., Tateo, D., Ammar, H. B., & Peters, J. (2022, January). Robot reinforcement learning on the constraint manifold. In Conference on Robot Learning (pp. 1357-1366). PMLR.
Q: Do I need to participate in the warm-up stage to get a prize?
A: No, you just need to participate in the Qualifying Stage. The warm-up is designed to allow participants to familiarize themselves with the environment and the software infrastructure.
Q: Will I be able to test my code on the real robot?
A: Only the first three teams will be able to deploy their approach on the real robot.
Q: How is the final ranking decided?
A: The final ranking will be decided in the last stage with a tournament, where participants will face each other in a full game.
Q: How often is updated the leaderboard?
A: The leaderboard is updated once per day.
Q: Which software is necessary for this challenge? Can I have more information about this software?
A: The challenge is based on the MushroomRL open-source reinforcement learning library. You can find the documentation for MushroomRL here. The environments are implemented using the MuJoCo simulator. You can find the documentation of MuJoCo here.