Training a Neural Network with Reinforcement learning

Question

I know the basics of feedforward neural networks, and how to train them using the backpropagation algorithm, but I'm looking for an algorithm that I can use for training an ANN online with reinforcement learning.

For example, the cart-pole swing up problem is one I'd like to solve with an ANN. In that case, I don't know what should be done to control the pendulum, I only know how close I am to the ideal position. I need to have the ANN learn based on reward and punishment. Thus, supervised learning isn't an option.

Another situation is something like the snake game, where feedback is delayed, and limited to goals and anti-goals, rather than reward.

I can think of some algorithms for the first situation, like hill-climbing or genetic algorithms, but I'm guessing they would both be slow. They might also be applicable in the second scenario, but incredibly slow, and not conducive to online learning.

My question is simple: Is there a simple algorithm for training an artificial neural network with reinforcement learning? I'm mainly interested in real-time reward situations, but if an algorithm for goal-based situations is available, even better.

Answer 1

Reinforcement learning means goal-oriented algorithms, which learn how to attain a complex objective (goal) or maximize along a particular dimension over many steps; for example, maximize the points won in a game over many moves.  

Some research papers on the topic:

• Efficient Reinforcement Learning Through Evolving Neural Network Topologies (2002)

• Reinforcement Learning Using Neural Networks, with Applications to Motor Control

• Reinforcement Learning Neural Network To The Problem Of Autonomous Mobile Robot Obstacle Avoidance

And some code:

• Code examples for neural network reinforcement learning.

You can check out more papers on Google Scholar. The above papers are the top search results on google.

Hope this answer helps.