feat(rewards): introduce distributional value function model

Browse Source

- Added a new distributional value function (DistributionalVF) model for RECAP, including its configuration, modeling, and processor components.
- Updated the rewards factory to support the new model type.
- Updated  to include the new model in the dependencies.

...

This commit is contained in:

Khalil Meftah

2026-06-10 15:24:50 +02:00

parent 49755a3d9e

commit 500c91ba92

8 changed files with 1300 additions and 337 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

uv.lock

Generated

+342 -337

File diff suppressed because it is too large Load Diff