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.
In this workshop, the attendees will get a hands-on understanding of the concepts and essential algorithms of reinforcement learning and deep reinforcement learning and how it can be used to build games. In fact, if you are a beginner-level data scientist or interested in learning advanced ML/AI topics, the workshop will be a great way to gain an in-depth understanding of reinforcement learning theory and programming techniques.
The full-day workshop, on reinforcement learning, will cover topics such as: introduction and the basics of learning paradigm; ingredients of reinforcement learning; dynamic programming; transfer and multi-task reinforcement learning; ethics involved; deep Q-learning and action-value function; applications of reinforcement learning and deep reinforcement learning etc. The workshop will also provide hands-on reinforcement learning frameworks like OpenAI Gym; Keras-RL; Nervana Systems Coach; Garage; Surreal; Tensorforce; Google Dopamine; and will give an introduction to policy-based methods and implementation of deep-Q network with PyTorch to play a game.
The participants are required to come with an open mind, seeking new ideas and possibilities. The workshop also comes with a few prerequisites like — basic to a moderate level understanding of python; basic grasp of Pandas, Numpy, Scikit-learn and other Python packages; acquaintance with the basics of deep learning, convolutional neural network, recurrent neural network; and familiarity with Google Colab and GPU environment. Further, attendees need to have an editor to run the python programs, preferably Google Colab Notebooks. However, if the attendees are working on a text editor application, they must install Pandas, Numpy, scikit-learn, TensorFlow, Pytorch and Keras. Participants are also expected to have a high-speed internet connection.
Upon completing the workshop, the attendees will get hands-on experience in some of the most used reinforcement learning frameworks. Key takeaways of the workshop include learning the structure and creating a reinforcement learning problem and the latest advancement in reinforcement learning. The workshop will also provide attendees with proficiency in building games using reinforcement learning and dealing with open problems in reinforcement learning. Attendees will also get a certificate on building reinforcement learning agents from scratch.
Details of the workshop:
Date: 20th of February 2021
Timings (Full day): 10:00 am to 5:00 pm (IST)
Pricing: $12.99 (workshop is free for ADaSci members)