Our MDP has 3 states: s 1 , s 2 , s 3 . The state transition probabilities are: ...
✅ The verified answer to this question is available below. Our community-reviewed solutions help you understand the material better.
Our MDP has 3 states: s1, s2, s3. The state transition probabilities are: p11=0, p12=0.4, p13=0.6. When leaving the state s1, the agent receives Rs1=2 reward. The state value function of the states s2 and s3 are: v2=8, v3=4. Calculate the v1 state value of the state s1. The discount factor γ=0.5.
Want instant access to all verified answers on elearning.aua.am?
Get Unlimited Answers To Exam Questions - Install Crowdly Extension Now!