Comments (2)
Hi,
Using several heads can allow them to specialize and attend to different parts of the input data, and it has shown to be beneficial in some use cases. However, the number of heads can be considered as a hyperparameter, and I don't know of any good tuning rule except for manual/grid search... On the intersection task, I think that I tried 2, 4 and 8 heads without seeing any significant effect (but 2 was better than 1). Also, note that with the current implementation, the dimensions of the attention features are shared between the heads, so (all things being equal) having more heads also means having smaller heads.
tldr: my advice is: try to change it, see if it helps ;)
from rl-agents.
I will try it, thanks a lot!!
from rl-agents.
Related Issues (20)
- hi, where is the code of computing social-attention and the code of updating the policy ? thanks. HOT 2
- 'Adam' object has no attribute 'get_updates' HOT 2
- Improve frontend for the observation carousel
- Agent compatibility for IntersectionEnv multiagent env HOT 2
- TypeError: must be real number, not NoneType HOT 11
- How can I obtain the accelaration information of vehicles? HOT 3
- What reward function did you use in IntersectionEnv? HOT 2
- Question about rl-agents HOT 1
- Some warnings during operation HOT 1
- Environment window resizing HOT 1
- training problem HOT 2
- Algorithmic issues HOT 3
- Display vehicle trajectory HOT 2
- The problem of reward performance HOT 2
- Some problems in the evaluation.py
- Some problems in the evaluation.py HOT 1
- Some issues regarding attention mechanisms HOT 1
- Display attention lines HOT 1
- AttributeError: 'Evaluation' object has no attribute 'seed'. and if it is feasible to rely solely on reinforcement learning to achieve automatic driving decision-making HOT 3
- Use a trained model HOT 2
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 rl-agents.