Tool profile

NVlabs/GDPO

stable

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

agentic-aigrpollmreasoningrltrlverl

Velocity score

0.02/ 10

[STARS]

452

[FORKS]

[CONTRIBUTORS]

[LAST_COMMIT]

2mo ago

30-day stars

0.02/ 10 score

last 33d

[SIGNAL_TRACE / 33_PT]

Score breakdown

345/ 1000

agents · NVlabs/GDPO

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

304

[INSTALL_VEL]

497

[ACTIVITY]

197

[COMMUNITY_SIGNAL]

279

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).