♻️ crazy refactor

configs/runner/mujoco_single.yaml

@@ -0,0 +1,7 @@
+# Single-env MuJoCo runner — mimics real hardware timing.
+# dt × substeps = 0.002 × 10 = 0.02 s → 50 Hz control, same as serial runner.
+
+num_envs: 1
+device: cpu
+dt: 0.002
+substeps: 10

configs/runner/serial.yaml

@@ -0,0 +1,11 @@
+# Serial runner — communicates with real hardware over USB/serial.
+# Always single-env, CPU-only.  Override port on CLI:
+#   python train.py runner=serial runner.port=/dev/ttyUSB0
+
+num_envs: 1
+device: cpu
+port: /dev/cu.usbserial-0001
+baud: 115200
+dt: 0.02                    # control loop period (50 Hz)
+no_data_timeout: 2.0        # seconds of silence before declaring disconnect
+encoder_jump_threshold: 200  # encoder tick jump → reboot detection