Deep Learning with TensorFlow

Source code for the FrozenLake-v0 problem

The following is the implementation of the Q-learning algorithm for the FrozenLake-v0 problem:

import gym import numpy as np env = gym.make('FrozenLake-v0') #Initialize table with all zeros Q = np.zeros([env.observation_space.n,env.action_space.n]) # Set learning parameters lr = .85 gamma = .99 num_episodes = 2000 #create lists to contain total rewards and steps per episode rList = [] for i in range(num_episodes): #Reset environment and get first new observation     s = env.reset()     rAll = 0     d = False     j = 0    #The Q-Table learning algorithm     while j < 99:         j+=1    #Choose an action by greedily (with noise) picking from Q table         a=np.argmax(Q[s,:]+\   np.random.randn(1,env.action_space.n)*(1./(i+1)))  ...