Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots
This provides a versatile tool for robotics researchers and developers to streamline reinforcement learning for mobile robots, though it is incremental as it builds on existing Unity ML-Agents technology.
The paper tackles the challenge of training mobile robots for locomotion tasks by introducing Unity RL Playground, an open-source framework that automates training in simulation with potential for real-world transfer, achieving one-click training and compatibility with diverse robot configurations.
This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotion tasks such as walking, running, and jumping in simulation, with the potential for seamless transfer to real hardware. Key features include one-click training for imported robot models, universal compatibility with diverse robot configurations, multi-mode motion learning capabilities, and extreme performance testing to aid in robot design optimization and morphological evolution. The attached video can be found at https://linqi-ye.github.io/video/iros25.mp4 and the code is coming soon.