Skip to content

Minor changes for python 3.6 #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
pathway wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Minor changes for python 3.6 #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions generate_buffer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,9 +20,9 @@

file_name = "DDPG_%s_%s" % (args.env_name, str(args.seed))
buffer_name = "Robust_%s_%s" % (args.env_name, str(args.seed))
print "---------------------------------------"
print "Settings: " + file_name
print "---------------------------------------"
print("---------------------------------------")
print("Settings: " + file_name)
print("---------------------------------------")

if not os.path.exists("./buffers"):
os.makedirs("./buffers")
Expand Down Expand Up @@ -53,7 +53,7 @@
if done:

if total_timesteps != 0:
print("Total T: %d Episode Num: %d Episode T: %d Reward: %f") % (total_timesteps, episode_num, episode_timesteps, episode_reward)
print("Total T: %d Episode Num: %d Episode T: %d Reward: %f" % (total_timesteps, episode_num, episode_timesteps, episode_reward))

# Reset environment
obs = env.reset()
Expand Down
14 changes: 7 additions & 7 deletions main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,9 +22,9 @@ def evaluate_policy(policy, eval_episodes=10):

avg_reward /= eval_episodes

print "---------------------------------------"
print "Evaluation over %d episodes: %f" % (eval_episodes, avg_reward)
print "---------------------------------------"
print("---------------------------------------")
print("Evaluation over %d episodes: %f" % (eval_episodes, avg_reward))
print("---------------------------------------")
return avg_reward


Expand All @@ -40,9 +40,9 @@ def evaluate_policy(policy, eval_episodes=10):

file_name = "BCQ_%s_%s" % (args.env_name, str(args.seed))
buffer_name = "%s_%s_%s" % (args.buffer_type, args.env_name, str(args.seed))
print "---------------------------------------"
print "Settings: " + file_name
print "---------------------------------------"
print("---------------------------------------")
print("Settings: " + file_name)
print("---------------------------------------")

if not os.path.exists("./results"):
os.makedirs("./results")
Expand Down Expand Up @@ -77,4 +77,4 @@ def evaluate_policy(policy, eval_episodes=10):
np.save("./results/" + file_name, evaluations)

training_iters += args.eval_freq
print "Training iterations: " + str(training_iters)
print("Training iterations: " + str(training_iters))
10 changes: 5 additions & 5 deletions train_expert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,9 +20,9 @@
args = parser.parse_args()

file_name = "DDPG_%s_%s" % (args.env_name, str(args.seed))
print "---------------------------------------"
print "Settings: " + file_name
print "---------------------------------------"
print("---------------------------------------")
print("Settings: " + file_name)
print("---------------------------------------")

if not os.path.exists("./pytorch_models"):
os.makedirs("./pytorch_models")
Expand Down Expand Up @@ -50,8 +50,8 @@

if done:

if total_timesteps != 0:
print("Total T: %d Episode Num: %d Episode T: %d Reward: %f") % (total_timesteps, episode_num, episode_timesteps, episode_reward)
if total_timesteps != 0:
print("Total T: %d Episode Num: %d Episode T: %d Reward: %f" % (total_timesteps, episode_num, episode_timesteps, episode_reward))
policy.train(replay_buffer, episode_timesteps)

# Save policy
Expand Down
2 changes: 1 addition & 1 deletion utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,4 +34,4 @@ def save(self, filename):
np.save("./buffers/"+filename+".npy", self.storage)

def load(self, filename):
self.storage = np.load("./buffers/"+filename+".npy")
self.storage = np.load("./buffers/"+filename+".npy",allow_pickle=True)