CODEWITHSUNDEEP
datasetreinforcement-learning
ashah
ashah

Reputation: 269

How to train a Deep Reinforcement Learning Network?

This is a conceptual question. I come from a Computer Vision background where the Object Detection DNNs are trained using a predefined dataset such as COCO, NYU-D etc and then the DNN is able to predict the results for an input image based on the training.

However, in the case of Deep Reinforcement Learning I am unable to find a dataset that can train Deep RL networks. Rather I find resources that talk about environment for training.

So the questions is whether Deep RL networks are required to be trained using environments only or is it possible to train them similar to Object Detection DNNs i.e by using some sort of dataset ?

Upvotes: 1

Views: 555

Answers (1)

Harry
Harry

Reputation: 96

This is a very common confusion in the AI community. Long story short, reinforcement learning (RL) method requires feedback (reward,state) from environment based on the action determined by RL. dataset is not able to provide that feedback. You can consider RL as a close-loop feedback system, whereas suerpervised learning (DNN) as the open-loop feedforward system.

To help you understand RL better. RL methods learn from the interaction with environment incrementally in the following steps:

  1. Initialize RL agent policy and/or value functions;
  2. Initialize the state that RL agent is starting with;
  3. RL agent determines an action based on current state;
  4. Action is applied to the environment;
  5. Environment reacts to the action and state is updated, a reward is generated;
  6. state and reward from the environment are transmitted to the RL agent;
  7. RL agent updates its policy and/or value functions based on the state and reward feedback;
  8. Then go back to step #3;

I suggest you to briefly read the RL text book from Richard Sutton: Reinforcement Learning: An Introduction. You can download free from here: https://web.stanford.edu/class/psych209/Readings/SuttonBartoIPRLBook2ndEd.pdf

Upvotes: 2

Related Questions