issues Search Results · repo:sweetice/Deep-reinforcement-learning-with-pytorch language:Python
Filter by
35 results
(125 ms)35 results
insweetice/Deep-reinforcement-learning-with-pytorch (press backspace or delete to remove)I met the error as follow: RuntimeError: one of the variables needed for gradient computation has been modified by an
inplace operation: [torch.cuda.FloatTensor [256, 1]], which is output 0 of AsStridedBackward0, ...
VansWaston
- 2
- Opened on Jan 15
- #50
Hello everyone. I am planning to create my own environment in Python using my aircraft s specifications. Most of the
code I see on GitHub uses pre-prepared environments from Gym. How can I use my own 6DOF ...
aminrbspace
- 2
- Opened on Jul 12, 2024
- #48
state = torch.from_numpy(state).float().unsqueeze(0) report this bug.
The input state is: image
The torch version is: 1.11.0+cu113.
Any suggestion is appreciated~~~
zhang-qiang-github
- 1
- Opened on Jun 3, 2024
- #47
In gridworld.py ,77 lines,self.position = [np.random.randint(tot_row), np.random.randint(tot_col)]. I think it should
modify self.position = [np.random.randint(self.world_row), np.random.randint(self.world_col)] ...
Wei-yao-Cheng
- Opened on Apr 7, 2024
- #46
img width= 893 alt= Screenshot 2023-03-30 at 8 46 07 PM src=
https://user-images.githubusercontent.com/37682760/229017694-94dc0496-6a74-4576-963b-b360778476a8.png
CajetanRodrigues
- 1
- Opened on Mar 31, 2023
- #45
If raise NotImplementedError, just modify the functions title of NormalizedActions class, modify _action to aciton and
_reverse_action to reverse_action.
QinwenLuo
- 2
- Opened on Dec 6, 2022
- #43
in sac.py s = torch.tensor([t.s for t in self.replay_buffer]).float().to(device) Traceback (most recent call last): File
D:\PycharmProject\Deep-reinforcement-learning-with-pytorch-master\Char09 SAC\SAC.py ...
aut6620
- 3
- Opened on May 23, 2022
- #38
the update value network should be:
alpha_w = 1e-3 # 初始化
optimizer_w = optim.Adam(**s_value_func**.parameters(), lr=alpha_w)
optimizer_w.zero_grad()
policy_loss_w =-delta
policy_loss_w.backward(retain_graph ...
hlhang9527
- 3
- Opened on Mar 21, 2022
- #37
log_prob should be multiplied by temperature factor (alpha) when calculating pi_loss in ALL implementations of SAC.
Darkness-hy
- 1
- Opened on Mar 11, 2022
- #36
In dist = Normal(mu, sigma) , sigma should be a positive value, but actor_net output can be negative, so action_log_prob
= dist.log_prob(action) can be nan.
Try:
import torch
a = torch.FloatTensor([1]).cuda() ...
Vinson-sheep
- 3
- Opened on Feb 16, 2022
- #35
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Restrict your search to the title by using the in:title qualifier.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.