MCPcopy Create free account
hub / github.com/lazyprogrammer/machine_learning_examples / main

Function main

rl2/mountaincar/pg_tf_random.py:235–261  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

233
234
235def main():
236 env = gym.make('MountainCarContinuous-v0')
237 ft = FeatureTransformer(env, n_components=100)
238 D = ft.dimensions
239 pmodel = PolicyModel(ft, D, [], [])
240 # init = tf.global_variables_initializer()
241 session = tf.InteractiveSession()
242 # session.run(init)
243 pmodel.set_session(session)
244 pmodel.init_vars()
245 gamma = 0.99
246
247 if 'monitor' in sys.argv:
248 filename = os.path.basename(__file__).split('.')[0]
249 monitor_dir = './' + filename + '_' + str(datetime.now())
250 env = wrappers.Monitor(env, monitor_dir)
251
252 totalrewards, pmodel = random_search(env, pmodel, gamma)
253 print("max reward:", np.max(totalrewards))
254
255 # play 100 episodes and check the average
256 avg_totalrewards = play_multiple_episodes(env, 100, pmodel, gamma, print_iters=True)
257 print("avg reward over 100 episodes with best models:", avg_totalrewards)
258
259 plt.plot(totalrewards)
260 plt.title("Rewards")
261 plt.show()
262
263
264if __name__ == '__main__':

Callers 1

pg_tf_random.pyFile · 0.70

Calls 6

set_sessionMethod · 0.95
init_varsMethod · 0.95
FeatureTransformerClass · 0.90
PolicyModelClass · 0.70
random_searchFunction · 0.70
play_multiple_episodesFunction · 0.70

Tested by

no test coverage detected