Comments (2)
See the documentation for attention mask here:
"attention_mask (torch.FloatTensor of shape (batch_size, sequence_length), optional) —
Mask to avoid performing attention on padding token indices.
Mask values selected in [0, 1]:
1 for tokens that are not masked,
0 for tokens that are masked."
This is not the same as the triangular matrix used when computing the attention values.
from decision-transformer.
Thanks @donthomasitos, I think you're very right. This looks like a bug from my point of view. I hope we're wrong :)
from decision-transformer.
Related Issues (20)
- Any reason for using different models for gym and atari experiments? HOT 2
- Is there a code for the shortest path search? HOT 1
- The setting of final token
- Why the padding is different for state, action, reward?
- Global position embedding and timesteps look wrong in atari HOT 2
- Bug in state and action prediction
- [IDEA] Code for dataset generation HOT 1
- Questions about dataset preprocessing
- AttributeError: 'GPT2Config' object has no attribute 'n_ctx' HOT 6
- Gsutil Error HOT 1
- why sample from multinomial distribution during evaluation in Atari?
- torch.stack bug
- how to print accurate in this code? HOT 2
- position embeddings do not vary between various time steps HOT 1
- Image Data
- Question about the output of the decision transformer HOT 3
- What should return to go be during inferencing? HOT 2
- MultiDiscrete Action Space HOT 1
- compilation error (MuJoCo) HOT 1
- Where are the datasets? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from decision-transformer.