比赛时间:即日起至2021年12月10日18:00
比赛规则:本次比赛为计时竞速赛,选手需通过比赛链接进入比赛,提交自己的模型,并获得自己的比赛成绩与名次。
选手的赛车需用最快的速度在赛道中完成三圈,同时避免偏离赛道(每次出界罚时3秒),并在 Leaderboard 中得到自己的最终成绩与名次。
比赛最终名次以比赛结束后 Leaderboard 的实时名次为准。
比赛奖励:线上挑战赛前10名的选手将收到邀请参与12月在上海举办的WAIC Amazon DeepRacer 线下赛(报销交通与酒店),同时所有奖品均在线下赛现场领取哦。
2、访问大赛官网提交模型:https://console.aws.amazon.com/deepracer/home#raceToken/zt7K_x95Q9q5yJ864g8vgg
扫码加入交流群,了解更多比赛信息,与众多技术大牛切磋哦~
以下是亚马逊云科技的开发大神写的示例代码,大家可以参考改进。
def reward_function(params):
'''
Example of rewarding the agent to follow center line
'''
# Read input parameters
track_width = params['track_width']
distance_from_center = params['distance_from_center']
speed = params['speed']
all_wheels_on_track = params['all_wheels_on_track']
progress = params['progress']
# Calculate 3 markers that are at varying distances away from the center line
marker_1 = 0.1 * track_width
marker_2 = 0.2 * track_width
marker_3 = 0.5 * track_width
# Give higher reward if the car is closer to center line and vice versa
if distance_from_center <= marker_1:
reward = 1.1
elif distance_from_center <= marker_2:
reward = 0.6
elif distance_from_center <= marker_3:
reward = 0.1
else:
reward = 1e-5 # likely crashed/ close to off track
if progress == 100:
reward = 5
if all_wheels_on_track:
reward = reward * (1 + speed * 0.2)
else:
reward = 1e-5
return float(reward)
还不熟悉Amazon DeepRacer?本周日下午直播,教你飙车!
点击阅读原文,立即注册账号参赛吧!