Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Type
/
to search
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
Uh oh!
There was an error while loading.
Please reload this page
.
Tencent-Hunyuan
/
UniRL
Public
Notifications
You must be signed in to change notification settings
Fork
60
Star
880
Code
Issues
18
Pull requests
48
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Issues
Pull requests
Actions
Projects
Security and quality
Insights
feat(algorithms): add AR PPO with GAE and value loss
- #259
#259
Merged
leviking98z-rgb
merged 11 commits into
Tencent-Hunyuan:main
Tencent-Hunyuan/UniRL:main
from
yhl48:feat/ar-ppo-gae
yhl48/UniRL:feat/ar-ppo-gae
Copy head branch name to clipboard
Aug 1, 2026
Conversation
Commits
11
(11)
Checks
Files changed
Merged
feat(algorithms): add AR PPO with GAE and value loss
#259
leviking98z-rgb
merged 11 commits into
Tencent-Hunyuan:main
Tencent-Hunyuan/UniRL:main
from
yhl48:feat/ar-ppo-gae
yhl48/UniRL:feat/ar-ppo-gae
Copy head branch name to clipboard
Commits
Commits on Jul 25, 2026
feat(models): add AR value head and GAE track wiring
Show description for 7395a83
yhl48
committed
7395a83
View commit details
Copy full SHA for 7395a83
Browse repository at this point
fix(models): restore lazy third-party imports in Qwen3
Show description for e858e8e
yhl48
committed
e858e8e
View commit details
Copy full SHA for e858e8e
Browse repository at this point
fix(models): require value head in replay forward path
Show description for 06aa5e3
yhl48
committed
06aa5e3
View commit details
Copy full SHA for 06aa5e3
Browse repository at this point
refactor(models): use ReplayResult for AR replay values
Show description for e913991
yhl48
committed
e913991
View commit details
Copy full SHA for e913991
Browse repository at this point
Commits on Jul 26, 2026
style: fix ruff format and unused variable for CI
Show description for e3aa596
yhl48
committed
e3aa596
View commit details
Copy full SHA for e3aa596
Browse repository at this point
refactor(types): index terminal rewards via cu_seqlens only
Show description for bd91950
yhl48
committed
bd91950
View commit details
Copy full SHA for bd91950
Browse repository at this point
feat(algorithms): add AR PPO with GAE and value loss
Show description for f40dcd0
yhl48
committed
f40dcd0
View commit details
Copy full SHA for f40dcd0
Browse repository at this point
Commits on Aug 1, 2026
fix(models): make value head FSDP dtype-safe
leviking98z-rgb
committed
74bef1c
View commit details
Copy full SHA for 74bef1c
Browse repository at this point
fix(models): preserve value-head and GAE correctness on current main
leviking98z-rgb
committed
0968556
View commit details
Copy full SHA for 0968556
Browse repository at this point
fix(algorithms): harden AR PPO integration after review
leviking98z-rgb
committed
cda2582
View commit details
Copy full SHA for cda2582
Browse repository at this point
Merge branch 'main' into feat/ar-ppo-gae
leviking98z-rgb
authored
cbfd6e6
View commit details
Copy full SHA for cbfd6e6
Browse repository at this point
You can’t perform that action at this time.
