myGym: Modular Toolkit for Visuomotor Robotic Tasks
Michal Vavrecka, Nikita Sokovnin, Megi Mejdrechova, Gabriela Sejnova,, Marek Otahal

TL;DR
myGym is a modular virtual robotic toolkit designed for reinforcement learning and visuomotor tasks, enabling easy transfer to real robots, customization, and support for intrinsic motivation and human-robot interaction scenarios.
Contribution
It introduces a flexible, modular simulation environment that supports visuomotor, unsupervised, and collaborative tasks, with pretrained visual modules and easy customization.
Findings
Supports transfer from simulation to real robots
Enables rapid prototyping with pretrained visual modules
Flexible environment for diverse visuomotor tasks
Abstract
We introduce a novel virtual robotic toolkit myGym, developed for reinforcement learning (RL), intrinsic motivation and imitation learning tasks trained in a 3D simulator. The trained tasks can then be easily transferred to real-world robotic scenarios. The modular structure of the simulator enables users to train and validate their algorithms on a large number of scenarios with various robots, environments and tasks. Compared to existing toolkits (e.g. OpenAI Gym, Roboschool) which are suitable for classical RL, myGym is also prepared for visuomotor (combining vision & movement) unsupervised tasks that require intrinsic motivation, i.e. the robots are able to generate their own goals. There are also collaborative scenarios intended for human-robot interaction. The toolkit provides pretrained visual modules for visuomotor tasks allowing rapid prototyping, and, moreover, users can…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Methods*Communicated@Fast*How Do I Communicate to Expedia? · Average Pooling · Dilated Convolution · Global Average Pooling · Dense Connections · Convolution · Adam · Experience Replay · 1x1 Convolution · Switchable Atrous Convolution
