num_envs: 1024       # MJX shines with many parallel envs
device: auto         # auto = cuda if available, else cpu
dt: 0.002
substeps: 10
history_length: 10   # RMA-style: 10-step window of (obs, action) pairs

rma_mode: "none"    # "none" | "teacher" | "deploy"

# ── Domain randomization (sim-to-real) ──────────────────────────────
# Full DR on GPU: latency + sensor noise + per-env dynamics scales
# (friction/damping/torque) are all applied inside the JIT step.
domain_rand:
  qpos_noise_std: 0.01         # rad   — encoder angle noise
  qvel_noise_std: 0.5          # rad/s — velocity-estimate noise (measured)
  action_delay_steps: [0, 2]   # control-step latency (0–40 ms)
  friction_scale: [0.6, 1.6]   # Coulomb-friction multiplier (per env)
  damping_scale: [0.6, 1.6]    # viscous-damping multiplier
  torque_scale: [0.85, 1.15]   # motor-constant / battery-voltage variation