def update_trials(self, trials):
count = 0
for trial in trials:
if trial["state"] == hyperopt.JOB_STATE_NEW:
if "submitted" not in trial or not trial["submitted"]:
# submit jobs and set status to running
hyperparam = self.unwrap_hyperparam(trial["misc"]["vals"])
full_path = self.make_full_path(hyperparam)
rt.run(self.setting, location=full_path, ids=self.ids,
parallelization="condor", force_rerun=False, block=False,
**hyperparam)
trial["submitted"] = True
else:
count += 1
#trial["state"] = hyperopt.JOB_STATE_RUNNING
# elif trial["state"] == hyperopt.JOB_STATE_RUNNING:
# check if all results files are there and set to ok
hyperparam = self.unwrap_hyperparam(trial["misc"]["vals"])
full_path = self.make_full_path(hyperparam)
finished_ids = rt.get_finished_ids(path=full_path)
if set(finished_ids).issuperset(set(self.ids)):
trial["state"] = hyperopt.JOB_STATE_DONE
print trial["tid"], "done"
trial["result"] = self.get_results(full_path)
print "Parameters", hyperparam
return count
def update_trials(self, trials):
count = 0
for trial in trials:
if trial["state"] == hyperopt.JOB_STATE_NEW:
if "submitted" not in trial or not trial["submitted"]:
# submit jobs and set status to running
hyperparam = self.unwrap_hyperparam(trial["misc"]["vals"])
full_path = self.make_full_path(hyperparam)
rt.run(self.setting, location=full_path, ids=self.ids,
parallelization="condor", force_rerun=False, block=False,
**hyperparam)
trial["submitted"] = True
else:
count += 1
#trial["state"] = hyperopt.JOB_STATE_RUNNING
# elif trial["state"] == hyperopt.JOB_STATE_RUNNING:
# check if all results files are there and set to ok
hyperparam = self.unwrap_hyperparam(trial["misc"]["vals"])
full_path = self.make_full_path(hyperparam)
finished_ids = rt.get_finished_ids(path=full_path)
if set(finished_ids).issuperset(set(self.ids)):
trial["state"] = hyperopt.JOB_STATE_DONE
print trial["tid"], "done"
trial["result"] = self.get_results(full_path)
print "Parameters", hyperparam
return count
def multiple_parallel_runs(varname, vrange, singlemap="9x9-2Path0.txt"):
'''Runs 5 seeds of experiment.
Results will be saved with special convention (for sake of more than 10 variables)
'''
params = rt.default_params()
params['mapf'] = singlemap
for i, v in enumerate(vrange):
params[varname] = v #update hyperparam object
print params
print "Running {0}: {1}".format(varname, v)
run("./TwoPathExperiments/trial_2pathsreward.py",
"./TwoPathExperiments/{0}/{1}/{2}".format(varname, singlemap, str('%02d' % i)),
ids=range(5), parallelization="joblib", force_rerun=True, **params)
def f(hyperparam):
"""function to optimize by hyperopt"""
# "temporary" directory to use
full_path = os.path.join(
path, "-".join([str(v) for v in list(hyperparam.values())]))
# execute experiment
rt.run(setting,
location=full_path,
ids=list(range(1, trials_per_point + 1)),
parallelization=parallelization,
force_rerun=False,
block=True,
**hyperparam)
# all jobs should be done
res = tres.load_results(full_path)
if objective == "max_steps":
m, s, n = tres.avg_quantity(res, "steps")
val = -m
std = s[-1]
elif objective == "min_steps":
m, s, n = tres.avg_quantity(res, "steps")
val = m
std = s[-1]
elif objective == "max_reward":
m, s, n = tres.avg_quantity(res, "return")
val = -m
std = s[-1]
else:
print("unknown objective")
weights = (np.arange(len(val)) + 1)**2
loss = old_div((val * weights).sum(), weights.sum())
print(time.ctime())
print("Parameters", hyperparam)
print("Loss", loss)
# use #steps/eps at the moment
return {
"loss": loss,
"num_trials": n[-1],
"status": hyperopt.STATUS_OK,
"std_last_mean": std
}
def f(hyperparam):
"""function to optimize by hyperopt"""
# "temporary" directory to use
full_path = os.path.join(
path,
"-".join([str(v) for v in hyperparam.values()]))
# execute experiment
rt.run(setting, location=full_path, ids=range(1, trials_per_point + 1),
parallelization=parallelization, force_rerun=False, block=True, **hyperparam)
# all jobs should be done
res = tres.load_results(full_path)
if objective == "max_steps":
m, s, n = tres.avg_quantity(res, "steps")
val = -m
std = s[-1]
elif objective == "min_steps":
m, s, n = tres.avg_quantity(res, "steps")
val = m
std = s[-1]
elif objective == "max_reward":
m, s, n = tres.avg_quantity(res, "return")
val = -m
std = s[-1]
else:
print "unknown objective"
weights = (np.arange(len(val)) + 1) ** 2
loss = (val * weights).sum() / weights.sum()
print time.ctime()
print "Parameters", hyperparam
print "Loss", loss
# use #steps/eps at the moment
return {"loss": loss,
"num_trials": n[-1],
"status": hyperopt.STATUS_OK,
"std_last_mean": std}
from rlpy.Tools.run import run
run("examples/tutorial/infTrackCartPole_rbfs.py", "./Results/Tutorial/InfTrackCartPole/RBFs",
ids=range(10), parallelization="joblib")
run("examples/tutorial/infTrackCartPole_tabular.py", "./Results/Tutorial/InfTrackCartPole/Tabular",
ids=range(10), parallelization="joblib")
from rlpy.Tools.run import run
import rlpy.Tools.results as rt
import os
import sys
if __name__ == '__main__':
experiment_name = sys.argv[1]
experiment_dir = os.path.expanduser("~/work/clipper/models/rl/")
result_dir = "./Results/" + experiment_name + "/"
run(experiment_dir + experiment_name + "Experiment.py",
result_dir,
ids=range(6),
parallelization="joblib")
paths = {experiment_name: result_dir}
merger = rt.MultiExperimentResults(paths)
fig = merger.plot_avg_sem("learning_steps", "return")
rt.save_figure(fig, result_dir + "plot.pdf")
