if not continue_execution: os.makedirs(main_outdir)
# Initiate learning information
with open(main_outdir + 'episode_data.csv', 'w') as csvRWRD:
csvRWRD_writer = csv.writer(csvRWRD, dialect='excel')
csvRWRD_writer.writerow([
'Episode', 'Goal', 'Steps', 'Reward', 'Total Goals',
'Average Steps'
])
csvRWRD.close()
last_time_steps = numpy.ndarray(0)
qlearn = qlearn.QLearn(actions=range(env.action_space.n),
alpha=0.1,
gamma=0.9,
epsilon=1,
qdir=qtabledir)
initial_epsilon = qlearn.epsilon
epsilon_discount = 0.9986
start_time = time.time()
total_goals = 0
total_succeed_steps = 0
total_episodes = 1000
highest_reward = -10000000
fewest_steps = 10000000
best_act = []
== 0) and (x != 0) and (x > render_skip) and (render_episodes < x):
env.render(close=True)
if __name__ == '__main__':
env = gym.make('GazeboProjectTurtlebot-v0')
outdir = '/tmp/gazebo_gym_experiments'
env = gym.wrappers.Monitor(env, outdir, force=True)
plotter = liveplot.LivePlot(outdir)
last_time_steps = numpy.ndarray(0)
qlearn = qlearn.QLearn(actions=range(env.action_space.n),
alpha=0.2,
gamma=0.8,
epsilon=0.0)
initial_epsilon = qlearn.epsilon
epsilon_discount = 0.9986
start_time = time.time()
total_goals = 0
total_succeed_steps = 0
total_episodes = 1001
highest_reward = -10000000
fewest_steps = 10000000
best_act = []
best_act_time = []