3 votes

Is it appropriate to represent 'total failure' as an absorbing state?

In an episodic problem, absorbing states are implemented to make the maths work similarly to continuing tasks. It allows one set of equations to cover two types of MDP (continuing and episodic). For ...
user avatar
  • 24.5k
1 vote

Can the state transition function be dynamic in reinforcement learning?

Is it possible to make the transition function change as the game progress? Yes, the normal way to do this would be to make the current time or time step $t$ part of the state $s$, so that equation 1 ...
user avatar
  • 24.5k
1 vote

What is the difference between a distribution model and a sampling model in Reinforcement Learning?

I think that your description is roughly correct, but I wouldn't call a "sampling model" a "model" because it doesn't necessarily model something, unless, for example, you are ...
user avatar
  • 34.5k

Only top scored, non community-wiki answers of a minimum length are eligible