1

I am going to work on a project which requires implementation of A2C model using Tensorflow 2.0. I am new in the Machine Learning field and also in Python. These are topics which I have covered theoretically:

- Different methods of Machine learning (supervised, unsupervised, reinforcement)
- Linear and Logistic Regression
- Required knowledge on Statistic and Probability
- Neural network
- Policy gradient
- Gradient Descent
- Basic of Tensorflow 2.0 (basic operations, preprocessing of Data)

Now I am a bit confused about what structure should I follow to become well familiar with Reinforcement learning, A2C model with Tensorflow and complete the project. I need some structured guidelines to study (even if possible from scratch).

Hi and welcome to Data Science Stack Exchange. It is hard to tell what you might need, since you have listed all of the topics necessary to complete your work. There are also free, open-source implementations of A2C, such as https://github.com/germain-hug/Deep-RL-Keras/tree/master/A2C I suggest you explain more specifically where you are stuck (creating the environment, deciding the reward structure), and give specific details about your problem. Use [edit] to add details. It is much more likely to get an answer to a single specific problem on this site, as opposed to a general guideline.

– Neil Slater – 2019-11-25T08:01:57.710Hie. Thank you for your reply. Can you tell me some online resources to study Tensorflow 2.0 from scratch (also with practical exercise)? I also need to know how to create an environment using Tensorflow. – EMT – 2019-11-25T12:13:10.690

I could not tell you any better than Google. TensorFlow's own site contains tutorials - have you tried those? Typically you would not develop an environment using machine learning tools, it is most often similar to writing a game. Details depend a

loton the target environment. – Neil Slater – 2019-11-25T12:44:03.943