Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
ADaM-BJTU authored Dec 10, 2024
1 parent d7e199b commit 7c0c532
Showing 1 changed file with 1 addition and 1 deletion.
2 changes: 1 addition & 1 deletion src/RL/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ The core component of this project is `RewardAggregater`, which supports flexibl
- `alpha` function (time decay factor)
- `gamma` (discount factor)

This tool can compute **intermediate rewards** and **final rewards** based on different model outputs (e.g., inference steps of language generation models) and supports offline processing.
This tool can compute **intermediate rewards** and **outcome rewards** based on different model outputs.

## Usage

Expand Down

0 comments on commit 7c0c532

Please sign in to comment.