19 lines
976 B
YAML
19 lines
976 B
YAML
max_steps: 1000
|
|
robot_path: assets/rotary_cartpole
|
|
reward_upright_scale: 1.0
|
|
|
|
# ── Regularisation penalties (prevent fast spinning) ─────────────────
|
|
motor_vel_penalty: 0.01 # penalise high motor angular velocity
|
|
motor_angle_penalty: 0.05 # penalise deviation from centre
|
|
action_penalty: 0.05 # penalise large actions (energy cost)
|
|
|
|
# ── Software safety limit (env-level, always applied) ────────────────
|
|
motor_angle_limit_deg: 90.0 # terminate episode if motor exceeds ±90°
|
|
|
|
# ── HPO search ranges ────────────────────────────────────────────────
|
|
hpo:
|
|
reward_upright_scale: {min: 0.5, max: 5.0}
|
|
motor_vel_penalty: {min: 0.001, max: 0.1}
|
|
motor_angle_penalty: {min: 0.01, max: 0.2}
|
|
action_penalty: {min: 0.01, max: 0.2}
|
|
max_steps: {values: [500, 1000, 2000]} |