Browse all 9 articles in this open-source series. A simulation-first series on Microduck reinforcement-learning environments and sim-to-real gates.
Featured starting point
A source-backed overview of Microduck RL environments, the mjlab loop, and sim-to-real safety gates.
Suggested learning path
01 → 09
A source-backed overview of Microduck RL environments, the mjlab loop, and sim-to-real safety gates.
Start with a pinned mjlab environment, inspect observations and rewards, and save a reproducible rollout.
Deploy training and evaluation workers with pinned simulators, GPU isolation, artifact storage, and a guarded hardware handoff.
Trace observations through actions, physics, reward shaping, termination, and policy updates in the Microduck loop.
Use deterministic fixtures to read environment registration, mjlab adapters, rewards, resets, runners, and checkpoint export.
Benchmark simulation throughput, GPU memory, parallel environments, checkpoint storage, and accepted-policy review.
Govern robot assets, checkpoints, telemetry, control interfaces, operator approvals, and incident recovery.
Choose a robotics RL stack by fidelity, throughput, assets, hardware path, reproducibility, and safety burden.
Design a Microduck RL project with task manifests, deterministic fixtures, policy cards, telemetry, and staged hardware gates.
