KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL
KlaskTron: An Open-Source Platform for Physical Adversarial Multi-Agent RL
This paper introduces KlaskTron, an open-source, low-cost (<$2500 USD) desktop-scale robotic testbed for adversarial multi-agent reinforcement learning (MARL). The platform is based on the dynamic tabletop game KLASK and features dual CoreXY gantries with high-torque brushless motors. It includes a complete ecosystem comprising hardware designs (CAD, BOM), a GPU-native digital twin in NVIDIA Isaac Lab for high-fidelity simulation, and a validated sim-to-real baseline using a learned neural actuator model that enables zero-shot policy transfer. All project assets, including assembly documentation, inference software, and MARL setup, are released publicly to ensure reproducibility.
The authors present KlaskTron, a low-cost open-source robotic testbed designed to enable physical adversarial multi-agent reinforcement learning, providing hardware designs, simulation environments, and evidence of zero-shot policy transfer.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
cost
2,500
View original evidence
ey barrier is infrastructural: physical platforms are often prohibitively expensive, require specialized facilities, or lack open mechanisms and designs for reproducibility. We introduce KlaskTron, an open-source, low-cost (<\$2500 USD), desktop-scale robotic testbed for adversarial MARL based on the dynamic tabletop game KLASK. The platform features dual CoreXY gantries with high-torque brushless motors, enabling th
Open source S3
- paper: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ey barrier is infrastructural: physical platforms are often prohibitively expensive, require specialized facilities, or lack open mechanisms and designs for reproducibility. We introduce KlaskTron, an open-source, low-cost (<\$2500 USD), desktop-scale robotic testbed for adversarial MARL based on the dynamic tabletop game KLASK. The platform features dual CoreXY gantries with high-torque brushless motors, enabling th
Open source S3
e high-speed, precise manipulation required for competitive play. Crucially, we provide a complete ecosystem: hardware designs (CAD, BOM), a GPU-native digital twin in NVIDIA Isaac Lab for high-fidelity modeling and simulation, and a validated sim-to-real baseline using a learned neural actuator model. We demonstrate that this baseline enables zero-shot policy transfer, with trained agents exhibiting emergent adversa
Open source S4
rial behaviors. To ensure full reproducibility of our results, all project assets are released publicly: hardware CAD/BOM and assembly documentation at [https://idscethzurich.github.io/klask_hardware], inference software stack at [https://github.com/IDSCETHZurich/klask_software] and the simulation and MARL setup at [https://github.com/IDSCETHZurich/klask_rl].
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org