Comments (2)
Hi, we learn mean for the policy but keep std fixed, so the policy is still stochastic. The advantage of doing so is that learning std sometimes might lead to premature policy collapse, which prevents exploration in harder environments.
from drqv2.
Okay thanks, that makes sense. But, wouldn't entropy account for this?
from drqv2.
Related Issues (20)
- Get to 96 frame throughput? HOT 8
- Replayloader doesn't work for Atari HOT 9
- How can i start with window 10. HOT 1
- Truncation for exploration? HOT 2
- Evaluation video overwritten HOT 2
- Not meant as an issue, but a little perplexed by feature_dim... HOT 5
- Reported frame-time question... HOT 3
- One more question, sorry... HOT 3
- custom env HOT 1
- Is it possible to do 1-step learning without done signal?
- DRQ-v2's Performance on Manipulator tasks (bring ball, insert ball, bring peg, insert peg)
- a certain chance to fail
- A question about num_train_frames
- Hyperparameters optimization
- Dreamerv2 learning curve
- Error when Running Training Command HOT 6
- Does drqv2 support multi-processing for the env interaction?
- Why using 'F.grid_sample()' in class RandomShiftsAug?
- Training Manipulation Tasks
- Memory Leak
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 drqv2.