AWS DeepRacer 奖励函数参考

以下是 AWS DeepRacer 奖励函数的技术参考。

主题

  • AWS DeepRacer 奖励函数的输入参数
  • AWS DeepRacer 奖励函数示例

AWS DeepRacer 奖励函数的输入参数

AWS DeepRacer 奖励函数的输入参数
PDF
AWS DeepRacer 奖励函数将字典对象作为输入。

def reward_function(params) :
    
    reward = ...

    return float(reward)

params 词典对象包含以下键/值对:

{
    "all_wheels_on_track": Boolean,        # flag to indicate if the agent is on the track
    "x": float,                            # agent's x-coordinate in meters
    "y": float,                            # agent's y-coordinate in meters
    "closest_objects": [int, int],         # zero-based indices of the two closest objects to the agent's current position of (x, y).
    "closest_waypoints": [int, int],       # indices of the two nearest waypoints.
    "distance_from_center": float,         # distance in meters from the track center 
    "is_crashed": Boolean,                 # Boolean flag to indicate whether the agent has crashed.
    "is_left_of_center": Boolean,          # Flag to indicate if the agent is on the left side to the track center or not. 
    "is_offtrack": Boolean,                # Boolean flag to indicate whether the agent has gone off track.
    "is_reversed": Boolean,                # flag to indicate if the agent is driving clockwise (True) or counter clockwise (False).
    "heading": float,                      # agent's yaw in degrees
    "objects_distance": [float, ],         # list of the objects' distances in meters between 0 and track_length in relation to the starting line.
    "objects_heading": [float, ],          # list of the objects' headings in degrees between -180 and 180.
    "objects_left_of_center": [Boolean, ], # list of Boolean flags indicating whether elements' objects are left of the center (True) or not (False).
    "objects_location": [(float, float),], # list of object locations [(x,y), ...].
    "objects_speed": [float, ],            # list of the objects' speeds in meters per second.
    "progress": float,                     # percentage of track completed
    "speed": float,                        # agent's speed in meters per second (m/s)
    "steering_angle": float,               # agent's steering angle in degrees
    "steps": int,                          # number steps completed
    "track_length": float,                 # track length in meters.
    "track_width": float,                  # width of the track
    "waypoints": [(float, float), ]        # list of (x,y) as milestones along the track center

}

输入参数的更多详细技术参考如下所示。


all_wheels_on_track
类型:Boolean

范围:(True:False)

一个 Boolean 标记,指示代理是在赛道上还是偏离赛道。如果车辆的任一车轮位于赛道边界外,则将车辆视为偏离赛道 (False)。如果车辆的所有车轮都在两个赛道边界内,则将车辆视为在赛道上 (True)。下图显示了代理在赛道上。

deepracer-reward-function-input-all_wheels_on_track-true.png

下图显示了代理偏离赛道。
deepracer-reward-function-input-all_wheels_on_track-false.png

示例:使用 all_wheels_on_track 参数的奖励函数

def reward_function(params):
    #############################################################################
    '''
    Example of using all_wheels_on_track and speed
    '''

    # Read input variables
    all_wheels_on_track = params['all_wheels_on_track']
    speed = params['speed']

    # Set the speed threshold based your action space
    SPEED_THRESHOLD = 1.0

    if not all_wheels_on_track:
        # Penalize if the car goes off track
        reward = 1e-3
    elif speed < SPEED_THRESHOLD:
        # Penalize if the car goes too slow
        reward = 0.5
    else:
        # High reward if the car stays on track and goes fast
        reward = 1.0

    return float(reward)
        

closest_waypoints
类型: [int, int]

范围:[(0:Max-1),(1:Max-1)]

最接近代理当前位置 (x, y) 的两个相邻 waypoint 的从零开始的索引。距离是根据与代理中心的欧氏距离来测量的。第一个元素指代理后面最近的路点,第二个元素指代理前面最近的路点。Max 是路点列表的长度。在waypoints的图示中,closest_waypoints 将为 [16, 17]。

示例:使用 closest_waypoints 参数的奖励函数。

以下示例奖励函数演示如何使用 waypoints、closest_waypoints 和 heading 来计算即时奖励。

AWS DeepRacer 支持以下库:数学、随机 NumPy SciPy、和 Shapely。要使用一个,请在函数定义的上方添加一个 import 语句def function_name(parameters)。import supported library

# Place import statement outside of function (supported libraries: math, random, numpy, scipy, and shapely)
# Example imports of available libraries
#
# import math
# import random
# import numpy
# import scipy
# import shapely

import math

def reward_function(params):
    ###############################################################################
    '''
    Example of using waypoints and heading to make the car point in the right direction
    '''

    # Read input variables
    waypoints = params['waypoints']
    closest_waypoints = params['closest_waypoints']
    heading = params['heading']

    # Initialize the reward with typical value
    reward = 1.0

    # Calculate the direction of the center line based on the closest waypoints
    next_point = waypoints[closest_waypoints[1]]
    prev_point = waypoints[closest_waypoints[0]]

    # Calculate the direction in radius, arctan2(dy, dx), the result is (-pi, pi) in radians
    track_direction = math.atan2(next_point[1] - prev_point[1], next_point[0] - prev_point[0])
    # Convert to degree
    track_direction = math.degrees(track_direction)

    # Calculate the difference between the track direction and the heading direction of the car
    direction_diff = abs(track_direction - heading)
    if direction_diff > 180:
        direction_diff = 360 - direction_diff

    # Penalize the reward if the difference is too large
    DIRECTION_THRESHOLD = 10.0
    if direction_diff > DIRECTION_THRESHOLD:
        reward *= 0.5

    return float(reward)

closest_objects
类型: [int, int]

范围:[(0:len(object_locations)-1), (0:len(object_locations)-1]

最接近代理当前位置 (x, y) 的两个物体的从零开始的索引。第一个索引指代理后面最近的物体,第二个索引指代理前面最近的物体。如果只有一个物体,则两个索引都为 0。

distance_from_center
类型: float

范围:0:~track_width/2

代理中心和赛道中心之间的位移(以米为单位)。当代理的任一车轮位于赛道边界外时可观察到的最大位移,并且根据赛道边界的宽度,它可以略小于或大于 track_width 的一半。

deepracer-reward-function-input-distance_from_center.png

示例:使用 distance_from_center 参数的奖励函数

def reward_function(params):
    #################################################################################
    '''
    Example of using distance from the center
    '''

    # Read input variable
    track_width = params['track_width']
    distance_from_center = params['distance_from_center']

    # Penalize if the car is too far away from the center
    marker_1 = 0.1 * track_width
    marker_2 = 0.5 * track_width

    if distance_from_center <= marker_1:
        reward = 1.0
    elif distance_from_center <= marker_2:
        reward = 0.5
    else:
        reward = 1e-3  # likely crashed/ close to off track

    return float(reward) 
        

heading
类型: float

范围:-180:+180

代理相对于坐标系 x 轴的前进方向(以度为单位)。

deepracer-reward-function-input-heading.png

示例:使用 heading 参数的奖励函数

有关更多信息,请参阅closest_waypoints:


is_crashed
类型: Boolean

范围:(True:False)

一个布尔标记,用于指示代理的最终状态是否为撞向另一个物体(True 或 False)

is_left_of_center
类型: Boolean

范围:[True : False]

一个 Boolean 标记,用于指示代理是位于赛道中心的左侧 (True) 还是右侧 (False)。

is_offtrack
类型: Boolean

范围:(True:False)

一个布尔标记,用于指示代理的最终状态是否为脱离赛道(True 或 False)。

is_reversed
类型: Boolean

范围:[True:False]

一个布尔标记,用于指示代理是顺时针行驶 (True) 还是逆时针行驶 (False)。

此参数在您针对每个过程改变方向时使用。

objects_distance
类型: [float, … ]

范围:[(0:track_length), … ]

环境中物体之间相对于起始线的距离列表。第 i 个元素测量沿赛道中心线第 i 个物体与起始线之间的距离。

注意 abs | (var1) - (var2)| = 汽车与物体的接近程度, WHEN var1 =
"objects_distance" and var2 =
params["progress"]*params["track_length"]
要获取车辆前方最近物体和车辆后方最近物体的索引,请使用“closest_objects”参数。

objects_heading
类型: [float, … ]

范围:[(-180:180), … ]

物体前进方向(以度为单位)列表。第 i 个元素测量第 i 个物体的前进方向。对于静止物体,其前进方向为 0。对于自动程序车辆,相应元素的值是车辆的前进角度。

objects_left_of_center
类型: [Boolean, … ]

范围:[True|False, … ]

布尔标记列表。第 i 个元素值指示第 i 个物体位于赛道中心的左侧 (True) 还是右侧 (False)。

objects_location
类型: [(x,y), ...]

范围:[(0:N,0:N), ...]

所有物体位置的列表,每个位置都是 (x, y) 的元组。

列表的大小等于赛道上的物体数。注意,物体可能是静止的障碍物,移动的自动程序车辆。

objects_speed
类型: [float, … ]

范围:[(0:12.0), … ]

赛道上物体的速度(米/秒)列表。对于静止物体,其速度为 0。对于机器人载具,该值是您在训练中设置的速度。

progress
类型: float

范围:0:100

赛道完成百分比。

示例:使用 progress 参数的奖励函数

有关更多信息,请参阅步骤。

speed
类型: float

范围:0.0:5.0

观察到的代理速度,以米/秒 (m/s) 为单位。

deepracer-reward-function-input-speed.png

示例:使用 speed 参数的奖励函数

有关更多信息,请参阅 all_wheels_on_track。

steering_angle
类型: float

范围:-30:30

前轮与代理中心线之间的转向角(以度为单位)。负号 (-) 表示向右转向,正号 (+) 表示向左转向。代理中心线不一定与赛道中心线平行,如下图所示。

deepracer-reward-function-steering.png

示例:使用 steering_angle 参数的奖励函数

def reward_function(params):
    '''
    Example of using steering angle
    '''

    # Read input variable
    abs_steering = abs(params['steering_angle']) # We don't care whether it is left or right steering

    # Initialize the reward with typical value
    reward = 1.0

    # Penalize if car steer too much to prevent zigzag
    ABS_STEERING_THRESHOLD = 20.0
    if abs_steering > ABS_STEERING_THRESHOLD:
        reward *= 0.8

    return float(reward)

steps
类型: int

范围:0:Nstep

完成的步骤数。步骤对应于代理按照当前策略所采取的操作。

示例:使用 steps 参数的奖励函数

def reward_function(params):
    #############################################################################
    '''
    Example of using steps and progress
    '''

    # Read input variable
    steps = params['steps']
    progress = params['progress']

    # Total num of steps we want the car to finish the lap, it will vary depends on the track length
    TOTAL_NUM_STEPS = 300

    # Initialize the reward with typical value
    reward = 1.0

    # Give additional reward if the car pass every 100 steps faster than expected
    if (steps % 100) == 0 and progress > (steps / TOTAL_NUM_STEPS) * 100 :
        reward += 10.0

    return float(reward)
           

track_length
类型: float

范围:[0:Lmax]

赛道长度(以米为单位)。Lmax is track-dependent.

track_width
类型: float

范围:0:Dtrack

赛道宽度(以米为单位)。

deepracer-reward-function-input-track_width.png


示例:使用 track_width 参数的奖励函数

def reward_function(params):
    #############################################################################
    '''
    Example of using track width
    '''

    # Read input variable
    track_width = params['track_width']
    distance_from_center = params['distance_from_center']

    # Calculate the distance from each border
    distance_from_border = 0.5 * track_width - distance_from_center

    # Reward higher if the car stays inside the track borders
    if distance_from_border >= 0.05:
        reward = 1.0
    else:
        reward = 1e-3 # Low reward if too close to the border or goes off the track

    return float(reward)


x, y
类型: float

范围:0:N

包含赛道的模拟环境的沿 x 和 y 轴的代理中心位置(以米为单位)。原点位于模拟环境的左下角。

deepracer-reward-function-input-x-y.png


waypoints
类型:[float, float] 的 list

范围:[[xw,0,yw,0] … [xw,Max-1, yw,Max-1]]

沿赛道中心排列、取决于赛道的 Max 里程的有序列表。每个里程碑都用 (xw,i, yw,i) 坐标来描述。对于环形赛道,第一个路径点与最后一个路径点相同。对于直道和其他非环形赛道,第一个路径点与最后一个路径点不同。

deepracer-reward-function-input-waypoints.png


示例:使用 waypoints 参数的奖励函数

有关更多信息,请参阅 closest_waypoints。

标签: none