Skip to content

Fix data type conflict in agents file #43

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
nguyen-thanh20 wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix data type conflict in agents file #43

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
ae3a8f5
Cast action from numpy.int64 to int
Jul 4, 2023
b9084f0
fix the dimension issues and convert numpy.int type to int type
Jul 4, 2023
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
2 changes: 1 addition & 1 deletion nasim/agents/bruteforce_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ def run_bruteforce_agent(env, step_limit=1e6, verbose=True):
act = next(act_iter)
cycle_complete = True

_, rew, done, env_step_limit_reached, _ = env.step(act)
_, rew, done, env_step_limit_reached, _ = env.step(int(act))
total_reward += rew

if cycle_complete and verbose:
Expand Down
9 changes: 4 additions & 5 deletions nasim/agents/ql_replay_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -247,10 +247,9 @@ def run_train_episode(self, step_limit):
episode_return = 0

while not done and not env_step_limit_reached and steps < step_limit:
a = self.get_egreedy_action(o, self.get_epsilon())

a = self.get_egreedy_action(o[0], self.get_epsilon())
next_o, r, done, env_step_limit_reached, _ = self.env.step(a)
self.replay.store(o, a, next_o, r, done)
self.replay.store(o[0], a, next_o, r, done)
self.steps_done += 1
mean_td_error, mean_v = self.optimize()
self.logger.add_scalar(
Expand Down Expand Up @@ -287,7 +286,7 @@ def run_eval_episode(self,
input("Initial state. Press enter to continue..")

while not done and not env_step_limit_reached:
a = self.get_egreedy_action(o, eval_epsilon)
a = self.get_egreedy_action(o[0], eval_epsilon)
next_o, r, done, env_step_limit_reached, _ = env.step(a)
o = next_o
episode_return += r
Expand All @@ -296,7 +295,7 @@ def run_eval_episode(self,
print("\n" + line_break)
print(f"Step {steps}")
print(line_break)
print(f"Action Performed = {env.action_space.get_action(a)}")
print(f"Action Performed = {env.action_space.get_action(int(a))}")
env.render(render_mode)
print(f"Reward = {r}")
print(f"Done = {done}")
Expand Down
2 changes: 1 addition & 1 deletion nasim/agents/random_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ def run_random_agent(env, step_limit=1e6, verbose=True):

while not done and not env_step_limit_reached and t < step_limit:
a = env.action_space.sample()
_, r, done, env_step_limit_reached, _ = env.step(a)
_, r, done, env_step_limit_reached, _ = env.step(int(a))
total_reward += r
if (t+1) % 100 == 0 and verbose:
print(f"{t}: {total_reward}")
Expand Down