Skip to content

fixed the typo in 'experience.py' and ... #12

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

fixed the typo in 'experience.py' and ... #12

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
4 changes: 2 additions & 2 deletions ptan/experience.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -493,8 +493,8 @@ def simple_dqn(model, **kwargs):
return QLearningPreprocessor(model=model, target_model=None, use_double_dqn=False, **kwargs)

@staticmethod
def target_dqn(model, target_model, **kwards):
return QLearningPreprocessor(model, target_model, use_double_dqn=False, **kwards)
def target_dqn(model, target_model, **kwargs):
return QLearningPreprocessor(model, target_model, use_double_dqn=False, **kwargs)

@staticmethod
def double_dqn(model, target_model, **kwargs):
Expand Down
13 changes: 6 additions & 7 deletions samples/rainbow/lib/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,10 +85,10 @@ def unpack_batch(batch):
def calc_loss_dqn(batch, net, tgt_net, gamma, cuda=False):
states, actions, rewards, dones, next_states = unpack_batch(batch)

states_v = Variable(torch.from_numpy(states))
next_states_v = Variable(torch.from_numpy(next_states), volatile=True)
actions_v = Variable(torch.from_numpy(actions))
rewards_v = Variable(torch.from_numpy(rewards))
states_v = torch.from_numpy(states)
next_states_v = torch.from_numpy(next_states)
actions_v = torch.from_numpy(actions)
rewards_v = torch.from_numpy(rewards)
done_mask = torch.ByteTensor(dones)
if cuda:
states_v = states_v.cuda()
Expand All @@ -100,10 +100,9 @@ def calc_loss_dqn(batch, net, tgt_net, gamma, cuda=False):
state_action_values = net(states_v).gather(1, actions_v.unsqueeze(-1)).squeeze(-1)
next_state_values = tgt_net(next_states_v).max(1)[0]
next_state_values[done_mask] = 0.0
next_state_values.volatile = False

expected_state_action_values = next_state_values * gamma + rewards_v
return nn.MSELoss()(state_action_values, expected_state_action_values)
expected_state_action_values = (next_state_values * gamma + rewards_v).detach()
return nn.functional.mse_loss(state_action_values, expected_state_action_values)


class RewardTracker:
Expand Down