AnymalTerrain.yaml

name: AnymalTerrain

physics_engine: ${..physics_engine}

env:
  numEnvs: ${resolve_default:2048,${...num_envs}}
  numObservations: 188
  numActions: 12
  envSpacing: 3.  # [m]

  terrain:
    staticFriction: 1.0  # [-]
    dynamicFriction: 1.0  # [-]
    restitution: 0.        # [-]
    # rough terrain only:
    curriculum: true
    maxInitMapLevel: 0
    mapLength: 8.
    mapWidth: 8.
    numLevels: 10
    numTerrains: 20
    # terrain types: [smooth slope, rough slope, stairs up, stairs down, discrete]
    terrainProportions: [0.1, 0.1, 0.35, 0.25, 0.2]
    # tri mesh only:
    slopeTreshold: 0.5

  baseInitState:
    pos: [0.0, 0.0, 0.62] # x,y,z [m]
    rot: [1.0, 0.0, 0.0, 0.0] # w,x,y,z [quat]
    vLinear: [0.0, 0.0, 0.0]  # x,y,z [m/s]
    vAngular: [0.0, 0.0, 0.0]  # x,y,z [rad/s]

  randomCommandVelocityRanges:
    # train
    linear_x: [-1., 1.] # min max [m/s]
    linear_y: [-1., 1.]   # min max [m/s]
    yaw: [-3.14, 3.14]    # min max [rad/s]

  control:
    # PD Drive parameters:
    stiffness: 80.0  # [N*m/rad]
    damping: 2.0     # [N*m*s/rad]
    # action scale: target angle = actionScale * action + defaultAngle
    actionScale: 0.5
    # decimation: Number of control action updates @ sim DT per policy DT
    decimation: 4

  defaultJointAngles:  # = target angles when action = 0.0
    LF_HAA: 0.03    # [rad]
    LH_HAA: 0.03    # [rad]
    RF_HAA: -0.03   # [rad]
    RH_HAA: -0.03   # [rad]

    LF_HFE: 0.4     # [rad]
    LH_HFE: -0.4    # [rad]
    RF_HFE: 0.4     # [rad]
    RH_HFE: -0.4    # [rad]

    LF_KFE: -0.8    # [rad]
    LH_KFE: 0.8     # [rad]
    RF_KFE: -0.8    # [rad]
    RH_KFE: 0.8     # [rad]


  learn:
    # rewards
    terminalReward: 0.0
    linearVelocityXYRewardScale: 1.0
    linearVelocityZRewardScale: -4.0
    angularVelocityXYRewardScale: -0.05
    angularVelocityZRewardScale: 0.5
    orientationRewardScale: -0.
    torqueRewardScale: -0.00002 
    jointAccRewardScale: -0.0005
    baseHeightRewardScale: -0.0
    actionRateRewardScale: -0.01
    fallenOverRewardScale: -1.0
    # cosmetics
    hipRewardScale: -0. #25

    # normalization
    linearVelocityScale: 2.0
    angularVelocityScale: 0.25
    dofPositionScale: 1.0
    dofVelocityScale: 0.05
    heightMeasurementScale: 5.0

    # noise 
    addNoise: true
    noiseLevel: 1.0 # scales other values
    dofPositionNoise: 0.01
    dofVelocityNoise: 1.5
    linearVelocityNoise: 0.1
    angularVelocityNoise: 0.2
    gravityNoise: 0.05
    heightMeasurementNoise: 0.06

    #randomization
    pushInterval_s: 15

    # episode length in seconds
    episodeLength_s: 20


sim:
  dt: 0.005
  use_gpu_pipeline: ${eq:${...pipeline},"gpu"}
  gravity: [0.0, 0.0, -9.81]
  add_ground_plane: False
  add_distant_light: False
  use_fabric: True
  enable_scene_query_support: False
  disable_contact_processing: True

  # set to True if you use camera sensors in the environment
  enable_cameras: False

  default_physics_material:
    static_friction: 1.0
    dynamic_friction: 1.0
    restitution: 0.0

  physx:
    worker_thread_count: ${....num_threads}
    solver_type: ${....solver_type}
    use_gpu: ${eq:${....sim_device},"gpu"} # set to False to run on CPU
    solver_position_iteration_count: 4
    solver_velocity_iteration_count: 0
    contact_offset: 0.02
    rest_offset: 0.0
    bounce_threshold_velocity: 0.2
    friction_offset_threshold: 0.04
    friction_correlation_distance: 0.025
    enable_sleeping: True
    enable_stabilization: True
    max_depenetration_velocity: 100.0

    # GPU buffers
    gpu_max_rigid_contact_count: 524288
    gpu_max_rigid_patch_count: 163840
    gpu_found_lost_pairs_capacity: 4194304
    gpu_found_lost_aggregate_pairs_capacity: 33554432
    gpu_total_aggregate_pairs_capacity: 4194304
    gpu_max_soft_body_contacts: 1048576
    gpu_max_particle_contacts: 1048576
    gpu_heap_capacity: 134217728
    gpu_temp_buffer_capacity: 33554432
    gpu_max_num_partitions: 8


  anymal:
    # -1 to use default values
    override_usd_defaults: False
    enable_self_collisions: True
    enable_gyroscopic_forces: False
    # also in stage params
    # per-actor
    solver_position_iteration_count: 4
    solver_velocity_iteration_count: 0
    sleep_threshold: 0.005
    stabilization_threshold: 0.001
    # per-body
    density: -1
    max_depenetration_velocity: 100.0