Comments (2)
Good question. I think the confusion here comes from the range of the tf.stop_gradient(log_pis + self._target_entropy)
term, which can in fact be either positive or negative due to log_pis
being the log density of the probability of action a at state s. @haarnoja correct me if I'm wrong.
from softlearning.
yeah, the magnitude of log_pis + self._target_entropy
can be either positive or negative. The gradient vanishes when log_pis == self._target_entropy
on expectation, as desired.
from softlearning.
Related Issues (20)
- SAC gradients weighted inconsistently
- Question on the soft q learning implementation HOT 1
- Question on initialization of alpha and entropy HOT 7
- Not use GPU failed call to cuInit: CUDA_ERROR_NO_DEVICE HOT 4
- `dm_control` `cheetah` `run` training stops suddenly HOT 3
- error when running example
- How can I generate eval/test output video of dm_control tasks?
- No rendering/headless mode available?
- No module named 'example.instruments' HOT 2
- target_entropy discrete_space HOT 2
- Implementation of automatic entropy temperature tuning(alpha loss) HOT 6
- SQL algorithm is not working HOT 1
- MultiGoal Env not working, please give instruction. HOT 6
- Error on installing with docker HOT 1
- Incompatible with ray 1.2.0 HOT 1
- Incompatible with tensorflow 2.4.0 HOT 1
- Differences between softlearning implementation and formula 18 in paper of alpha loss
- using deterministic policy in enviroment like lunarlander?
- why target entropy is -dim(A)?
- The issue of softlearning implementation 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 softlearning.