g4dn.2xlarge：性价比较高的训练方式，基于GPU 加速，训练速度稍快于 DeepRacer console 训练p3.2xlarge：训练速度远快于DeepRacer console 训练，快速迭代模型，取得训练成果

AmazonKinesisVideoStreamsCloudWatchS3

git clone https://github.com/aws-deepracer-community/deepracer-for-cloud.git

cd deepracer-for-cloud && ./bin/prepare.shsudo reboot

### 添加PUBKEYwget -qO - http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub | sudo apt-key add -### 更新sudo apt-get update### 重新执行,请确保您不在 deepracer-for-cloud目录中，请回到ubuntu的home目录下cd deepracer-for-cloud && ./bin/prepare.sh### 重启sudo reboot

E: Could not get lock /var/lib/dpkg/lock-frontend - open (11: Resource temporarily unavailable)E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), is another process using it?

sudo rm /var/lib/dpkg/lock-frontendsudo rm /var/lib/dpkg/lock### 重新执行,请确保您不在 deepracer-for-cloud目录中，请回到ubuntu的home目录下cd deepracer-for-cloud && ./bin/prepare.sh### 重启sudo reboot

### 请确保您此时在ubuntu的home目录下cd deepracer-for-cloud/ && bin/init.sh -c aws -a gpu

source bin/activate.sh

reward_function.py #奖励函数文件hyperparameters.json #训练信息文件model_metadata.json #车俩信息文件

   def reward_function(params):    '''    Example of penalize steering, which helps mitigate zig-zag behaviors    '''
    # Read input parameters    distance_from_center = params['distance_from_center']    track_width = params['track_width']    steering = abs(params['steering_angle']) # Only need the absolute steering angle
    # Calculate 3 marks that are farther and father away from the center line    marker_1 = 0.1 * track_width    marker_2 = 0.25 * 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    elif distance_from_center <= marker_2:        reward = 0.5    elif distance_from_center <= marker_3:        reward = 0.1    else:        reward = 1e-3  # likely crashed/ close to off track
    # Steering penality threshold, change the number based on your action space setting    ABS_STEERING_THRESHOLD = 15
    # Penalize reward if the car is steering too much    if steering > ABS_STEERING_THRESHOLD:        reward *= 0.8
    return float(reward)

   {    "batch_size": 64,    "beta_entropy": 0.01,    "discount_factor": 0.995,    "e_greedy_value": 0.05,    "epsilon_steps": 10000,    "exploration_type": "categorical",    "loss_type": "huber",    "lr": 0.0003,    "num_episodes_between_training": 20,    "num_epochs": 10,    "stack_size": 1,    "term_cond_avg_score": 350.0,    "term_cond_max_episodes": 1000,    "sac_alpha": 0.2  }

   {    "action_space": [        {            "steering_angle": -30,            "speed": 0.6        },        {            "steering_angle": -15,            "speed": 0.6        },        {            "steering_angle": 0,            "speed": 0.6        },        {            "steering_angle": 15,            "speed": 0.6        },        {            "steering_angle": 30,            "speed": 0.6        }    ],    "sensor": ["FRONT_FACING_CAMERA"],    "neural_network": "DEEP_CONVOLUTIONAL_NETWORK_SHALLOW",    "training_algorithm": "clipped_ppo",    "action_space_type": "discrete",    "version": "3"}

DR_LOCAL_S3_BUCKET=<创建的bucket名字>DR_UPLOAD_S3_BUCKET=<创建的bucket名字>

sed -i '1i\DR_LOCAL_S3_BUCKET=<创建的bucket名字>' run.envsed -i '1i\DR_UPLOAD_S3_BUCKET=<创建的bucket名字>' run.env

### 安装python 3.8sudo apt-get -y install python3.8
sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 2

### 执行如下代码,使此处配置生效dr-update

dr-upload-custom-files

dr-start-training

### 这是上一次训练存放文件夹，请查看S3存储桶中的文件夹名称DR_LOCAL_S3_MODEL_PREFIX=<本次训练存放S3存储桶的目录>### 确定培训或评估是否应基于在上一个会话中创建的模型DR_LOCAL_S3_PRETRAINED=True### 设置本次训练的目录DR_LOCAL_S3_PRETRAINED_PREFIX=<上一次训练存放S3存储桶的目录>### 本次训练从上一次训练的checkpoint设置 默认为 lastDR_LOCAL_S3_PRETRAINED_CHECKPOINT=best

dr-update-env

dr-upload-custom-files

dr-start-training

dr-start-training -w

W: GPG error: http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  Release: The following signatures couldn't be verified because the public key is not available: NO_PUBKEY F60F4B3D7FA2AF80E: The repository 'http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64  Release' is not signed.N: Updating from such a repository can't be done securely, and is therefore disabled by default.N: See apt-secure(8) manpage for repository creation and user configuration details.

wget -qO - http://developer.download.nvidia.com/compute/machine-learning/repos/ubuntu1804/x86_64/7fa2af80.pub | sudo apt-key add -
sudo apt-get update

sudo apt-get install python3.8sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.8 2

第一个参数--install表示向update-alternatives注册服务名。
第二个参数是注册最终地址，成功后将会把命令在这个固定的目的地址做真实命令的软链，以后管理就是管理这个软链；
( --install link name path priority)
其中link为系统中功能相同软件的公共链接目录，比如/usr/bin/java(需绝对目录);name为命令链接符名称,如java path为你所要使用新命令、新软件的所在目录 priority为优先级，当命令链接已存在时，需高于当前值，因为当alternative为自动模式时,系统默认启用priority高的链接;# 整数 根据版本号设置的优先级（更改的优先级需要大于当前的）
第三个参数：服务名，以后管理时以它为关联依据。
第四个参数，被管理的命令绝对路径。
第五个参数，优先级，数字越大优先级越高。

E: Could not get lock /var/lib/dpkg/lock-frontend - open (11: Resource temporarily unavailable)E: Unable to acquire the dpkg frontend lock (/var/lib/dpkg/lock-frontend), is another process using it?

$ sudo rm /var/lib/dpkg/lock-frontend$ sudo rm /var/lib/dpkg/lock

dr-start-training -w