📄️ Introduction
SuperDex Gym is a reinforcement-learning (RL) framework built on the SuperDex Physics
📄️ Installation and Setup
Install SuperDex Gym
📄️ Running Example Environments
SuperDex Gym provides example scripts for running its environments, along with sample environments to try.
📄️ Examples
Purpose
📄️ Environment Class API
Use this page for the shared runtime API implemented by MochiEnv. For the
📄️ Benchmarking
Prerequisites
📄️ Authoring a Custom Environment
The MochiEnv class is the base class for all SuperDex Gym environments. It
📄️ Training with Large Batches
SuperDex Gym scales RL training by combining two-tier vectorization with scene sharing
📄️ Training with Ray/RLlib
SuperDex Gym provides a Ray/RLlib integration for RL training on SuperDex Physics
📄️ Rendering
SuperDex Gym environments use superdex.physics.viewer.Viewer, the SuperDex
📄️ Visualizing Training History
apps/rllib/visualizetraininghistory.py combines per-checkpoint rollout videos