Comments (3)
By definition, if the agent thinks the agent's actions are better than actions in datasets, the sum of this advantage becomes negative.
This metrics indicates confidence of the agent against dataset actions.
from d3rlpy.
Thanks for your reply.
Should this score be bigger or smaller or 0?
I think if the dataset is expert behavior, the score is 0 represent the Q function is better,am I right?
from d3rlpy.
Yes, the smaller the score bcomes, the better the agent thinks. If it's zero, the policy actions are the exactly same as the dataset actions.
from d3rlpy.
Related Issues (20)
- [BUG] Question / Possible bug - observation data changing when loaded into TransitionMiniBatch() HOT 9
- [BUG] CQL Crashing HOT 3
- [Question] Question about log parameters HOT 2
- [BUG] current overwriting of transitions in the buffer causes problems in to_mdp_dataset() HOT 6
- [QUESTION] Early stopping HOT 2
- [REQUEST] Vectorized / multiple env support HOT 2
- [BUG] Error in fitted q evaluation example HOT 3
- [REQUEST] How can I use Transformer to be a Encoder? HOT 3
- [REQUEST] Adding Cal-QL HOT 2
- [Question] - Increasing model capacity HOT 2
- Models' Logits return, HOT 2
- [Question] How to append online transitions with pre-existing d4rl buffer in finetuning training? HOT 10
- [REQUEST] For next release, add the option to specify the ensemble reduction method as parameter of QFunc Factory
- Discrete version of MOPO / COMBO
- [REQUEST] Multi dimensional action space HOT 9
- TD3PlusBC.predict fails HOT 2
- [REQUEST] There is some typo in the math description of IQL algorithm HOT 1
- [REQUEST] Support other logging services as well as tensorboard HOT 3
- [QUESTION] How to use MOPO on offline datasets? HOT 3
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 d3rlpy.