投稿時間:2021-08-01 05:14:31 RSSフィード2021-08-01 05:00 分まとめ(15件)

カテゴリー等	サイト名等	記事タイトル・トレンドワード等	リンクURL	頻出ワード・要約等/検索ボリューム	登録日
Program	[全てのタグ]の新着質問一覧｜teratail（テラテイル）	.htaccessファイルを使ってリダイレクト(内部転送)したい	https://teratail.com/questions/352204?rss=all	htaccessファイルを使ってリダイレクト内部転送したいこんにちは。	2021-08-01 04:02:32
Ruby	Railsタグが付けられた新着投稿 - Qiita	Rails scaffoldコマンドで REST APIの作成	https://qiita.com/Hashimoto-Noriaki/items/56ec73a7ff2e3bde812d	apionlyはtrueにすることによってAPI実装で必要な部分だけが作成されるようになるオプション。	2021-08-01 04:21:52
海外TECH	DEV Community	Fine-tuning the performance of the DeepRacer model	https://dev.to/aws-builders/fine-tuning-the-performance-of-the-model-4pjo	Fine tuning the performance of the DeepRacer modelIn the first part of the AWS DeepRacer Blog series we saw how to create your AWS DeepRacer Model How cool is to watch your AWS DeepRacer car navigating autonomously every corner and turn in the circuit with your Reinforcement Learning model guiding it Now its time to fine tune the model so that we will try to clock the best time We will try to dive deeper into this tutorial and discuss more on the Action Space Reward Function and Hyper parameter tuning I have explained of creating and fine tuning the model using two algorithms and action spaces You can choose either one and ignore the rest Understanding the fundamentals Reinforcement Learning AlgorithmsWe can train models using either of two RL AlgorithmsProximal Policy Optimization PPO Soft Actor Critic SAC The main differences between the two algorithms arePPOSACWorks in both discrete and continuous action spacesWorks in a continuous action spaceOn policyOff policyUses entropy regularizationAdds entropy to the maximization objectiveTo know more about the algorithms check this link Action SpaceAction Space is the set of actions that is subjected to Maximum speed Speed Granularity Maximum Steering Angle and Steering angle Granularity At a particular instance of the input image from the sensor Front facing camera the model tries to pick one of the actions and the evaluates the reward obtained for the particular action Discrete Action Space The set of actions is defined by the user by specifying the maximum steering angle speed values and their respective granularities to generate the corresponding combinations of speed and steering actions Therefore the policy returns a discrete distribution of actions Continuous Action Space The policy only outputs two discrete values These values are interpreted to be the mean and standard deviation of a continuous normal distribution You define a range for speed and steering angle The action for an observed state is chosen from this user defined range of speed and steering by sampling the normal distribution defined by the mean and standard deviation returned from the policy Hyperparameters Hyperparameters are variables to control your reinforcement learning training They can be tuned to optimize the training time and model performance We have provision to fine tune seven hyperparameters We will try to understand how each hyperparameter influences model training Hyperparameter tuning is all about iterative improvement through trial and error method Gradient descent batch size The batch is a subset of an experience buffer that is composed of images captured by the camera mounted on the AWS DeepRacer vehicle and actions taken by the vehicle Number of epochs The number of passes through the training data to update the neural network weights during gradient descent Learning rate The learning rate controls how much a gradient descent or ascent update contributes to the network weights Entropy The added uncertainty helps the AWS DeepRacer vehicle explore the action space more broadly Discount factor The discount factor of means the current state is independent of future steps whereas the discount factor means that contributions from all of the future steps are included Loss type The type of objective function to update the network weights The number of experience episodes between each policy updating iteration The size of the experience buffer used to draw training data from for learning policy network weights SAC Alpha Value You can tune the amount of entropy to use in SAC with the hyperparameter SAC alpha with a value between and The maximum value of the SAC alpha uses the whole entropy value of the policy and favors exploration The minimum value of SAC alpha recovers the standard RL objective and there is no entropy bonus to incentivize the exploration A good SAC alpha value to kick off your first model is Reward FunctionThe reward function and the action space go hand in hand The reward function must be compatible with the values specified in the action list Last time we had selected one of the default reward function and trained the model Though that s the best way to start we need to understand the parameters of the vehicle input and design our own reward function to clock the best time The parameter that is passed to the reward function is params which is a Python Dictionary object I recommend you to read the official documentation and understand each parameter here Creating your vehicleIn your DeepRacer Console head to Your Garage in the side Nav Pane Creating vehicle Discrete Action SpaceClick Create Vehicle and give a suitable name of your choice and select any vehicle shell and click Next In the Vehicle Mod Specifications select Camera as the sensor Since we are going to race in Time Trials and click NextIn the Action Space Choose your action space type select Discrete and change the maximum and granularity values and notice the action list gets updated These action list define the behaviour of the model on the track Click Finish and your Discrete Action Space Vehicle is ready Creating vehicle Continuous Action SpaceFollow same steps in creating a new vehicle and giving new name and selecting the Camera as Sensor For Choose your action space type select Continuous Once you are ready with the vehicles you should have your vehicles listed in the Garage Create a modelGive a name for the model you are creating In this blog the model deepracerblog ppo for Discrete and deepracerblog sac for Continuous Action Space and select Environment Simulation as ReInvent Track For Race type select the type for this post we select Time trial Training Algorithms and Hyperparametersdeepracerblog ppo ModelTraining Algorithm PPOHyperparameters Configure the parametersAgent Select the Model you have created with discrete continuous action space deepracerblog ppo ModelTraining Algorithm PPOHyperparameters Configure the parametersAgent Select the Model you have created with discrete continuous action space Once you have fine tuned your model hyper parameters Choose Next Lastly you can write a reward function to configure your vehicle based on the hyperparameters and the total training time Click Validate to validate the reward function Training and Evaluating the modelWe need to specify the stopping time for the model training But there is a catch here If we train our model for lesser time there is a high chance of model underfitting that is the car may not perform well If the model trained for higher time the model may experience overfitting that is the model may perform really well for the current track you had trained for but may not perform well in other tracks To achieve the generalization we need to set optimum hours of training so that the model converges From other fellow developers it is said that hours of training yields good result Keep an eye on the evaluation Simulation and the Logs of the model so that you can improve in future models Now we are ready to conquer the checkered flag Do participate in AWS DeepRacer League and secure top position Additional Resources AWS DeepRacer e learning course for free For source code and get started pack see For more information about AWS DeepRacer see For more information about AWS Training and Certification see To troubleshoot and collaborate about the AWS DeepRacer see	2021-07-31 19:03:23
海外TECH	Engadget	Rivian may build its first international EV factory in the UK	https://www.engadget.com/rivian-uk-ev-factory-plans-193124496.html?src=rss	Rivian may build its first international EV factory in the UKRivian might not be focused solely on expanding its US production Sky Newssources claim the EV designer is in talks with the British government to build a manufacturing plant near Bristol The discussions aren t yet in late stages but the focus is reportedly on production for the vehicles themselves rather than batteries although there was room for an all encompassing Tesla style gigafactory Rival proposals have come from Germany and the Netherlands Sky claimed If the UK plant did go ahead though the government could supposedly invest quot well over quot £ billion about billion Rivian declined to comment There s certainly pressure to commit to international expansion Rivian has just one factory a former Mitsubishi plant in Illinois and it only just unveiled plans for a second American facility that might also produce batteries That output could limit potential sales especially outside of North America and might hamper Amazon s electric delivery van rollout This could help Rivian scale to counter rivals like Tesla and Volkswagen both of which are rapidly growing their EV manufacturing bases The UK intends to ban sales of combustion engine cars in and that means switching local production to EVs A Rivian factory could help the country transition to EV manufacturing not to mention encourage sales that would make public acceptance that much stronger	2021-07-31 19:31:24
ニュース	BBC News - Home	Afghanistan: Fighting rages as Taliban besiege three key cities	https://www.bbc.co.uk/news/world-asia-58040141	areas	2021-07-31 19:10:05
ニュース	BBC News - Home	South Africa 27-9 British and Irish Lions: Springboks level series in fiery encounter	https://www.bbc.co.uk/sport/rugby-union/58041234	South Africa British and Irish Lions Springboks level series in fiery encounterThe British and Irish Lions series with South Africa will go to a decider after the Springboks win a fiery second Test at Cape Town Stadium	2021-07-31 19:32:48
ビジネス	ダイヤモンド・オンライン - 新着記事	CAの世界にもある陰湿なイジメ、「人生に役立つ」切り抜け方を元チーフパーサーが伝授 - from AERAdot.	https://diamond.jp/articles/-/278040	CAの世界にもある陰湿なイジメ、「人生に役立つ」切り抜け方を元チーフパーサーが伝授fromAERAdot憧れの職業の一つであるCAキャビン・アテンダント。	2021-08-01 04:55:00
ビジネス	ダイヤモンド・オンライン - 新着記事	加齢臭対策！市販ボディソープ＆せっけん11選【ニオイの原因と予防法も解説】 - 男のオフビジネス	https://diamond.jp/articles/-/277761	配合	2021-08-01 04:50:00
ビジネス	ダイヤモンド・オンライン - 新着記事	新日本酒紀行「盛升」 - 新日本酒紀行	https://diamond.jp/articles/-/277427	全国新酒鑑評会	2021-08-01 04:45:00
ビジネス	ダイヤモンド・オンライン - 新着記事	夏休みに山陰・山陽のパワースポット巡りはいかが？絶景を見て運気アップ！ - 地球の歩き方ニュース＆レポート	https://diamond.jp/articles/-/277986	久しぶり	2021-08-01 04:40:00
ビジネス	ダイヤモンド・オンライン - 新着記事	アルコール摂取で新たにがんを発症、2020年に世界で74万人の衝撃 - ヘルスデーニュース	https://diamond.jp/articles/-/278169	アルコール摂取で新たにがんを発症、年に世界で万人の衝撃ヘルスデーニュースアルコール摂取が関連して、年に世界で万人が新たにがんを発症したとする研究結果が発表された。	2021-08-01 04:35:00
ビジネス	ダイヤモンド・オンライン - 新着記事	多品種少量生産、短納期にこだわり、ワイヤーハーネス産業で成長を遂げる - しんきん経営情報-ウチのイチ押し！	https://diamond.jp/articles/-/277678	多品種少量生産	2021-08-01 04:30:00
ビジネス	ダイヤモンド・オンライン - 新着記事	ステンレスハンガーや野菜チップスなど、自社ブランド品をネット販売して高評価 - しんきん経営情報-トップインタビュー	https://diamond.jp/articles/-/277677	経営情報	2021-08-01 04:25:00
ビジネス	ダイヤモンド・オンライン - 新着記事	古い知識にしがみついてばかりの「残念な人」にならないための効果的なインプット法とは？ - 知的戦闘力を高める 独学の技法	https://diamond.jp/articles/-/277099	可処分時間	2021-08-01 04:20:00
ビジネス	東洋経済オンライン	狭い家に引っ越したら｢町のアイドル｣になった訳 周りに壁を作ってきた私が突然｢いい人｣に | 買わない生活 | 東洋経済オンライン	https://toyokeizai.net/articles/-/444532?utm_source=rss&utm_medium=http&utm_campaign=link_back	東洋経済オンライン	2021-08-01 04:30:00