config.lwf = args.lwf
config.lwf_loss = args.lwf_loss
config.lwf_weight = args.lwf_weight
config.num_old_actions = int(args.num_old_actions)
return config
def print_config(config):
print 'Current config:\n'
variables = zip(vars(config).keys(), vars(config).values())
for var, val in sorted(variables):
print var + ' = ' + str(val)
if __name__ == '__main__':
args = parse_args()
my_config = modify_config(args)
print_config(my_config)
with tf.device('/gpu:' + str(args.gpu)):
# make env
env = gym.make(my_config.env_name)
env = wrap_dqn(env)
model = NatureQN(env, my_config)
model.initialize_eval()
model.evaluate()
if my_config.record:
model.record()
If so, please report your hyperparameters.
You'll find the results, log and video recordings of your agent every 250k under
the corresponding file in the results folder. A good way to monitor the progress
of the training is to use Tensorboard. The starter code writes summaries of different
variables.
To launch tensorboard, open a Terminal window and run
tensorboard --logdir=results/
Then, connect remotely to
address-ip-of-the-server:6006
6006 is the default port used by tensorboard.
"""
if __name__ == '__main__':
# make env
env = gym.make(config.env_name)
env = MaxAndSkipEnv(env, skip=config.skip_frame)
env = PreproWrapper(env,
prepro=greyscale,
shape=(80, 80, 1),
overwrite_render=config.overwrite_render)
# load model
model = NatureQN(env, config)
model.initialize()
loaded = load_model(model)
assert loaded != False, "Loading failed"
# evaluate one episode of data
model.evaluate(env, 1)