814 B
814 B
Documentation
Design & architecture (/design)
- 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)
- Environment: MuJoCo environment interaction, state retrieval, and configuration.
- Simulate: Simulation rendering.