1595420040

Autonomous vehicles become popular nowadays, so does deep reinforcement learning. This post can provide you with an idea to set up the environment for you to begin learning and experimenting with deep reinforcement learning for autonomous vehicles. Besides, I will share the first experiment I’ve done with Deep-Q-Network for a self-driving car on the race track in the simulator.

First, I’ll show you a short demo of my experiment. The .gif image highlights the steps of training a car to drive autonomously at a right turn for about 12 hours. In this experiment, the input for training the navigation model is the image frames recorded from a camera mounted on the head-front of the car. The bottom right window shows the live recording of that camera.

The 8x-fast-motion clip highlights the 12 hours of training a DQN model for the car at a right turn. Observations are the RGB frames from the head-front camera of the car.

There are 3 main components are used to conduct this experiment. Those are AirSim (run on Unreal Engine), Open AI Gym, and Keras-RL. Here I introduce briefly those main components if you are not familiar with those yet.

- AirSim is an add-on run on game engines like Unreal Engine(UE) or Unity. AirSim is developed as a platform for AI research to experiment with deep learning, computer vision, and reinforcement learning algorithms for autonomous vehicles.
- OpenAI Gym provides a range of game environments to play and evaluate reinforcement learning algorithms.
- Keras-RL is the python library implementing different deep reinforcement learning algorithms based on Keras. Keras-RL works with OpenAI Gym out of the box. This means that evaluating and playing around with different algorithms is easy.

The system diagram shows the components and their connections.

For my environment setup, I used Unreal Engine as the game engine with the map RaceCourse which offers several race tracks. Meanwhile, AirSim provides the car and APIs to control it (e.g: steering, acceleration), also the APIs to record images. So I can say that I already have a car driving game to play with.

The next step is connecting this driving game to the deep reinforcement learning tools Keras-RL and OpenAI Gym. To do that, first, a customized OpenAI Gym environment was created, this customized Gym environment calls the necessary AirSim APIs, like controlling the car or capturing images. As Keras-RL works with Gym environment, it means now Keras-RL algorithms can interact with the game through the customized Gym environment.

After combining the above components together, I’ve already had a framework to experiment with deep reinforcement learning for autonomous vehicles. One additional thing I need to do before running the first experiment is locating the race track in the map because the location of the track will be required to determine the reward for the car during training and evaluation, but this kind of information is not available in the map yet. To locate the track I put some waypoints manually in the center of the road, and measure the width of the road. With the list of waypoints, I can locate the track approximately. Note that these waypoints will be invisible once the game starts.

#autonomous-vehicles #airsim #keras-rl #openai-gym #deep learning

1618317562

View more: https://www.inexture.com/services/deep-learning-development/

We at Inexture, strategically work on every project we are associated with. We propose a robust set of AI, ML, and DL consulting services. Our virtuoso team of data scientists and developers meticulously work on every project and add a personalized touch to it. Because we keep our clientele aware of everything being done associated with their project so there’s a sense of transparency being maintained. Leverage our services for your next AI project for end-to-end optimum services.

#deep learning development #deep learning framework #deep learning expert #deep learning ai #deep learning services

1617355640

The Association of Data Scientists (AdaSci), a global professional body of data science and ML practitioners, is holding a full-day workshop on building games using reinforcement learning on Saturday, February 20.

Artificial intelligence systems are outperforming humans at many tasks, starting from driving cars, recognising images and objects, generating voices to imitating art, predicting weather, playing chess etc. AlphaGo, DOTA2, StarCraft II etc are a study in reinforcement learning.

Reinforcement learning enables the agent to learn and perform a task under uncertainty in a complex environment. The machine learning paradigm is currently applied to various fields like robotics, pattern recognition, personalised medical treatment, drug discovery, speech recognition, and more.

With an increase in the exciting applications of reinforcement learning across the industries, the demand for RL experts has soared. Taking the cue, the Association of Data Scientists, in collaboration with Analytics India Magazine, is bringing an extensive workshop on reinforcement learning aimed at developers and machine learning practitioners.

#ai workshops #deep reinforcement learning workshop #future of deep reinforcement learning #reinforcement learning #workshop on a saturday #workshop on deep reinforcement learning

1595573880

In this post, we will investigate how easily we can train a Deep Q-Network (DQN) agent (Mnih et al., 2015) for Atari 2600 games using the Google reinforcement learning library Dopamine. While many RL libraries exist, this library is specifically designed with **four essential features** in mind:

- Easy experimentation
- Flexible development
- Compact and reliable
- Reproducible

_We believe these principles makes _

_Dopamine _one of the. Additionally, we even got the library to work on Windows, which we think isbest RL learning environment available today!quite a feat

In my view, the visualization of any trained RL agent is an **absolute must** in reinforcement learning! Therefore, we will (of course) include this for our own trained agent at the very end!

We will go through all the pieces of code required (which is** minimal compared to other libraries**), but you can also find all scripts needed in the following Github repo.

The general premise of deep reinforcement learning is to

“derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations.”

- Mnih et al. (2015)

As stated earlier, we will implement the *DQN model* by *Deepmind*, which only uses raw pixels and game score as input. The raw pixels are processed using convolutional neural networks similar to image classification. The primary difference lies in the **objective function**, which for the DQN agent is called the *optimal action-value function*

where_ rₜ *is the maximum sum of rewards at time t discounted by γ, obtained using a behavior policy* π = P(a_∣_s)_ for each observation-action pair.

There are relatively many details to Deep Q-Learning, such as *Experience Replay* (Lin, 1993) and an _iterative update rule. _Thus, we refer the reader to the original paper for an excellent walk-through of the mathematical details.

One key benefit of DQN compared to previous approaches at the time (2015) was the ability to outperform existing methods for Atari 2600 games using the **same set of hyperparameters** and **only pixel values and game score as input**, clearly a tremendous achievement.

This post does not include instructions for installing Tensorflow, but we do want to stress that you can use **both the CPU and GPU versions**.

Nevertheless, assuming you are using `Python 3.7.x`

, these are the libraries you need to install (which can all be installed via `pip`

):

```
tensorflow-gpu=1.15 (or tensorflow==1.15 for CPU version)
cmake
dopamine-rl
atari-py
matplotlib
pygame
seaborn
pandas
```

#reinforcement-learning #q-learning #games #machine-learning #deep-learning #deep learning

1603735200

The Deep Learning DevCon 2020, DLDC 2020, has exciting talks and sessions around the latest developments in the field of deep learning, that will not only be interesting for professionals of this field but also for the enthusiasts who are willing to make a career in the field of deep learning. The two-day conference scheduled for 29th and 30th October will host paper presentations, tech talks, workshops that will uncover some interesting developments as well as the latest research and advancement of this area. Further to this, with deep learning gaining massive traction, this conference will highlight some fascinating use cases across the world.

Here are ten interesting talks and sessions of DLDC 2020 that one should definitely attend:

**Also Read:** Why Deep Learning DevCon Comes At The Right Time

**By Dipanjan Sarkar**

**About: **Adversarial Robustness in Deep Learning is a session presented by Dipanjan Sarkar, a Data Science Lead at Applied Materials, as well as a Google Developer Expert in Machine Learning. In this session, he will focus on the adversarial robustness in the field of deep learning, where he talks about its importance, different types of adversarial attacks, and will showcase some ways to train the neural networks with adversarial realisation. Considering abstract deep learning has brought us tremendous achievements in the fields of computer vision and natural language processing, this talk will be really interesting for people working in this area. With this session, the attendees will have a comprehensive understanding of adversarial perturbations in the field of deep learning and ways to deal with them with common recipes.

Read an interview with Dipanjan Sarkar.

**By Divye Singh**

**About: **Imbalance Handling with Combination of Deep Variational Autoencoder and NEATER is a paper presentation by Divye Singh, who has a masters in technology degree in Mathematical Modeling and Simulation and has the interest to research in the field of artificial intelligence, learning-based systems, machine learning, etc. In this paper presentation, he will talk about the common problem of class imbalance in medical diagnosis and anomaly detection, and how the problem can be solved with a deep learning framework. The talk focuses on the paper, where he has proposed a synergistic over-sampling method generating informative synthetic minority class data by filtering the noise from the over-sampled examples. Further, he will also showcase the experimental results on several real-life imbalanced datasets to prove the effectiveness of the proposed method for binary classification problems.

**By Dongsuk Hong**

**About:** This is a paper presentation given by Dongsuk Hong, who is a PhD in Computer Science, and works in the big data centre of Korea Credit Information Services. This talk will introduce the attendees with machine learning and deep learning models for predicting self-employment default rates using credit information. He will talk about the study, where the DNN model is implemented for two purposes — a sub-model for the selection of credit information variables; and works for cascading to the final model that predicts default rates. Hong’s main research area is data analysis of credit information, where she is particularly interested in evaluating the performance of prediction models based on machine learning and deep learning. This talk will be interesting for the deep learning practitioners who are willing to make a career in this field.

#opinions #attend dldc 2020 #deep learning #deep learning sessions #deep learning talks #dldc 2020 #top deep learning sessions at dldc 2020 #top deep learning talks at dldc 2020

1598250000

Although the field of deep learning is evolving extremely fast, unique research with the potential to get us closer to Artificial General Intelligence (AGI) is rare and hard to find. One exception to this rule can be found in the field of meta-learning. Recently, meta-learning has also been applied to Reinforcement Learning (RL) with some success. The paper “Discovering Reinforcement Learning Agents” by Oh et al. from DeepMind provides a new and refreshing look at the application of meta-learning to RL.

**Traditionally, RL relied on hand-crafted algorithms **such as Temporal Difference learning (TD-learning) and Monte Carlo learning, various Policy Gradient methods, or combinations thereof such as Actor-Critic models. These RL algorithms are usually finely adjusted to train models for a very specific task such as playing Go or Dota. One reason for this is that multiple hyperparameters such as the discount factor γ and the bootstrapping parameter λ need to be tuned for stable training. Furthermore, the very update rules as well as the choice of predictors such as value functions need to be chosen diligently to ensure good performance of the model. The entire process has to be performed manually and is often tedious and time-consuming.

DeepMind is trying to change this with their latest publication. In the paper, the authors propose a **new meta-learning approach that discovers the learning objective as well as the exploration procedure by interacting with a set of simple environments**. They call the approach the **Learned Policy Gradient (LPG)**. The most appealing result of the paper is that the algorithm is able to effectively generalize to more complex environments, suggesting the potential to discover novel RL frameworks purely by interaction.

In this post, I will try to explain the paper in detail and provide additional explanation where I had problems with understanding. Hereby, I will stay close to the structure of the paper in order to allow you to find the relevant parts in the original text if you want to get additional details. Let’s dive in!

#meta-learning #reinforcement-learning #machine-learning #ai #deep-learning #deep learning