Comments (2)
lokitoth
commented on August 29, 2024
Simple repro case where lack of model traps us in explore mode, returns action id = 0 for both slots.
from reinforcement_learning.
jackgerrits
commented on August 29, 2024
Looking at the repro, it looks like the model was started with the incorrect VW command line, cb_explore_adf but it should be ccb_explore_adf, but there is also more in the command line which handles model free exploration. In this case the default command line should be used.
Regardless, I just fixed a few bugs that may have still impacted this. I've added a test to verify model free exploration.
from reinforcement_learning.
Related Issues (20)
- Expose all report_outcome methods from C#
- Improve our windows build situation HOT 1
- Do not crash in ccb::predict is not successful
- schema v2 bug HOT 1
- example_gen bug with multiple rewards HOT 1
- pdrop is not turned off with setting interaction.queue.mode and observation.queue.mode to block
- [example_gen] Add support to control ccb slot_id generation
- Testing scenarios for parsing v2 files
- Windows solution in not buildable from folders with spaces
- [binary-log] Implement activation logic. HOT 1
- Flaky MacOS CI
- Add Dedup tests (dedup_test.cc) to the unit test project + fix some dedup tests
- [ci] request: have daily run with latest VW repo HOT 2
- [rl.cli.net] logs are not generated when configured to produce them locally. HOT 2
- Fix wheels produced by CI HOT 4
- 'http.timeout' config should accept values over 30 seconds
- Unit tests are not respecting conditional build
- Unit tests for multistep binary joiner
- Build Issue: Can't build with RAPIDJSON_SYS_DEP=OFF
- Flaky unit test(s)
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 reinforcement_learning.