Practical Reinforcement Learning: Develop self-evolving, intelligent agents with OpenAI Gym, Python and Java by Dr. Engr. S.M. Farrukh Akhtar

Author:Dr. Engr. S.M. Farrukh Akhtar [Akhtar, Dr. Engr. S.M. Farrukh]
Language: eng
Format: azw3
Tags: COM004000 - COMPUTERS / Intelligence (AI) and Semantics
Publisher: Packt Publishing
Published: 2017-10-20T04:00:00+00:00

#for obstacle for Nan at (1,1)

var_matrix_policy[1,1] = numP.NaN

var_matrix_policy[0,3] = var_matrix_policy[1,3] = -1

# Matrix action-state (intilize with random values)

parm_Matrix_Action_State_ = numP.random.random_sample((4,12))

Finally, we have the main loop of the algorithm, which is not so different from the loop used for the Monte Carlo prediction:

for var_epochs_ in range(var_Eepsilon_):

# New episode starting

var_list_episode = list()

# First observation would reset and return

_var_obser_ = environment.reset(var_Exploring_Starts=True)

_var_IsStarting_ = True

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.