Toggle navigation
JUPYTER
FAQ
View as Code
Python 3 (Spyder) Kernel
View on GitHub
Execute on Binder
Download Notebook
gt_rl_course
week_3
Notebook
Exercises Chapter 3 Markov Decision Processes
¶
p51 Ex 3.1 Devise three tasks in MDP framework
¶
Ex 3.2 Exceptions to MDP
¶
Ex 3.3 The problem of driving
¶
Ex. 3.6 Pole balancing (Cartpole!)
¶
Ex 3.7 robot in maze
¶
Ex 3.8 calculate returns G
¶
Ex 3.9 calculate return G
¶
Ex 3.12 v_pi
¶
Ex 3.14 verify bellman equation for gridworld example
¶
Ex 3.17 bellman equation for action values
¶
Ex 3.20 optimal state-value for golf example
¶
Ex 3.21 optimal action-value for putting in golf example
¶
Ex 3.22 optimal policies for MDP
¶
Ex 3.24 compute optimal value for best state in the Gridworld
¶
In [ ]: