Documentation

Design & architecture (/design)

If you are interested in the "why did you do it like this?"

• Actor/critic architecture: Description of the actor-critic pipeline.
• Communication: Message propagation, Nerve-Net style.
• Controllers: Macroscopig brain toplogy, centralized, arm-level, segment-level.
• Input/output: Description of the model's input and output.
• Learning algorithm: RL techniques, i.e. PPO.
• Reward function: Goals, fitness tracking, and reward structures.

API reference (/api)

If you are interested in the "how do I use it?"

• Training: How to configure and run experiments.
• Tracking & Monitoring: Setting up WandB and TensorBoard to monitor runs.
• Simulation: Visualizing and evaluating models.
• Environment: MuJoCo environment interaction and configuration.
• Analysis: Comparing checkpoints and generating plots.
• Evaluation: Evaluating checkpoints and comparing fault tolerance.