Markov decision process

Markov decision process

• 1.
  Markov Decision Process Prof.Neeraj Bhargava Kapil Chauhan Department of Computer Science School of Engineering & Systems Sciences MDS University, Ajmer
• 2.
  Introduction  Reinforcement Learningis a type of Machine Learning.  It allows machines and software agents to automatically determine the ideal behavior within a specific context, in order to maximize its performance.
• 3.
  Cont..  In theproblem, an agent is supposed to decide the best action to select based on his current state.  When this step is repeated, the problem is known as a Markov Decision Process.
• 4.
  Process of MDP
• 5.
  Markov Decision Process (MDP)model contains:  A set of possible world states S.  A set of Models.  A set of possible actions A.  A real valued reward function R(s,a).  A policy the solution of Markov Decision Process.
• 6.
  Model:  A Stateis a set of tokens that represent every state that the agent can be in.  A Model (sometimes called Transition Model) gives an action’s effect in a state. In particular, T(S, a, S’) defines a transition T where being in state S and taking an action ‘a’ takes us to state S’ (S and S’ may be same).
• 7.
  Cont..  An ActionA is set of all possible actions. A(s) defines the set of actions that can be taken being in state S.  A Reward is a real-valued reward function. R(s) indicates the reward for simply being in the state S.  A Policy is a solution to the Markov Decision Process. A policy is a mapping from S to a. It indicates the action ‘a’ to be taken while in state S.
• 8.
  Assignment  Explain MarkovDecision Process with example.