Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Jun 6, 2025

• Fix formatting (#90)

  garrett4wade

  authored
  448bb05View commit details

  Copy full SHA for 448bb05

  Browse repository at this point

• [Feature] Switch dataset path / model path to HF location to ease community usage (#82)

  Show description for de134b4
  Lyken17

  authored
  de134b4View commit details

  Copy full SHA for de134b4

  Browse repository at this point

Commits on Jun 4, 2025

• update readme (#78)

  garrett4wade

  authored
  b768e5cView commit details

  Copy full SHA for b768e5c

  Browse repository at this point

• [Doc] update blog to discuss staleness (#76)

  Show description for ae4b03d
  samjia2000

  authored
  ae4b03dView commit details

  Copy full SHA for ae4b03d

  Browse repository at this point

• fix (#77)

  garrett4wade

  authored
  15024d8View commit details

  Copy full SHA for 15024d8

  Browse repository at this point

• add hf links in readme and blog (#75)

  Show description for 67dc056
  

  GurrenLagann97

  and

  hcy

  authored
  67dc056View commit details

  Copy full SHA for 67dc056

  Browse repository at this point

Commits on Jun 3, 2025

• [Doc] Update README. (#74)

  Show description for d56df51
  

  garrett4wade

  and

  samjia2000

  authored
  d56df51View commit details

  Copy full SHA for d56df51

  Browse repository at this point

• [Doc] Add doc for reproducing released models (#73)

  Show description for 2d4d937
  

  garrett4wade

  and

  samjia2000

  authored
  2d4d937View commit details

  Copy full SHA for 2d4d937

  Browse repository at this point

• [Doc] Add verl benchmark scripts (#71)

  Show description for ad6e5bd
  garrett4wade

  authored
  ad6e5bdView commit details

  Copy full SHA for ad6e5bd

  Browse repository at this point

• [Feature] Update Dockerfile to v0.3.0 (#70)

  Show description for 326dfe3
  garrett4wade

  authored
  326dfe3View commit details

  Copy full SHA for 326dfe3

  Browse repository at this point

Commits on Jun 2, 2025

• [Doc] Mark the equivalent between zero-staleness and synchronous PPO (#69)

  garrett4wade

  authored
  2e5728aView commit details

  Copy full SHA for 2e5728a

  Browse repository at this point

• add doc (#68)

  garrett4wade

  authored
  fabe59aView commit details

  Copy full SHA for fabe59a

  Browse repository at this point

• add async doc (#67)

  garrett4wade

  authored
  ab20f94View commit details

  Copy full SHA for ab20f94

  Browse repository at this point

• [Doc] add dataset customization docs (#66)

  Show description for ac7a9c5
  

  3 peopleauthored
  ac7a9c5View commit details

  Copy full SHA for ac7a9c5

  Browse repository at this point

Commits on Jun 1, 2025

• [Doc] Add doc for reproducing benchmark results (#65)

  Show description for 11a34df
  garrett4wade

  authored
  11a34dfView commit details

  Copy full SHA for 11a34df

  Browse repository at this point

• [Doc] Fix documentation for using Docker containers and customized agents (#64)

  Show description for ce4d735
  garrett4wade

  authored
  ce4d735View commit details

  Copy full SHA for ce4d735

  Browse repository at this point

• [Fix] Fix tutorial async_ppo script and doc structure (#63)

  Show description for afe5a2c
  garrett4wade

  authored
  afe5a2cView commit details

  Copy full SHA for afe5a2c

  Browse repository at this point

• [Doc & Fix] Simplify the environment setup procedure (#62)

  Show description for 4fab3ac
  garrett4wade

  authored
  4fab3acView commit details

  Copy full SHA for 4fab3ac

  Browse repository at this point

Commits on May 30, 2025

• [Feature] Add link to documentation in README (#61)

  garrett4wade

  authored
  d87c898View commit details

  Copy full SHA for d87c898

  Browse repository at this point

• [Feature] Create docs and examples for multi-turn agent RL (#60)

  Show description for 473eeb2
  

  3 peopleauthored
  473eeb2View commit details

  Copy full SHA for 473eeb2

  Browse repository at this point

• [Feature] Support behavior importance weight capping and update evaluation scripts (#59)

  Show description for c0200f1
  

  3 peopleauthored
  c0200f1View commit details

  Copy full SHA for c0200f1

  Browse repository at this point

Commits on May 29, 2025

• [CI] Try to fix doc CI (#58)

  Show description for 0815bb6
  garrett4wade

  authored
  0815bb6View commit details

  Copy full SHA for 0815bb6

  Browse repository at this point

• [CI] Fix doc CI again (#57)

  Show description for b337560
  garrett4wade

  authored
  b337560View commit details

  Copy full SHA for b337560

  Browse repository at this point

• [CI] Fix doc CI (#56)

  Show description for 409fa98
  garrett4wade

  authored
  409fa98View commit details

  Copy full SHA for 409fa98

  Browse repository at this point

Commits on May 28, 2025

• . (#55)

  garrett4wade

  authored
  b240a9cView commit details

  Copy full SHA for b240a9c

  Browse repository at this point

• add doc ci (#54)

  garrett4wade

  authored
  d13b517View commit details

  Copy full SHA for d13b517

  Browse repository at this point

• [Feature] Amend yaml configurations for Ray experiments (#53)

  Show description for 7826fdb
  

  9 peopleauthored
  7826fdbView commit details

  Copy full SHA for 7826fdb

  Browse repository at this point

• [Feature & Doc & Bug Fix] Add docs, simplified ray-based scripts, and fix issues to stablize asynchronous experiments (#52)

  Show description for cf46993
  

  9 peopleauthored
  cf46993View commit details

  Copy full SHA for cf46993

  Browse repository at this point

Commits on May 26, 2025

• Update issue templates (#48)

  garrett4wade

  authored
  89cc3a7View commit details

  Copy full SHA for 89cc3a7

  Browse repository at this point

• Support asynchronous RL training, Qwen3, and the latest SGLang (#47)

  Show description for c60d128
  

  9 peopleauthored
  c60d128View commit details

  Copy full SHA for c60d128

  Browse repository at this point

Commits on May 25, 2025

• Delete .github/PULL_REQUEST_TEMPLATE directory (#46)

  garrett4wade

  authored
  f7ab31dView commit details

  Copy full SHA for f7ab31d

  Browse repository at this point

• Create bugfix.md (#45)

  garrett4wade

  authored
  5236f38View commit details

  Copy full SHA for 5236f38

  Browse repository at this point

• Add

  garrett4wade

  authored
  919b287View commit details

  Copy full SHA for 919b287

  Browse repository at this point

• Update and rename feature-request-issue-template.md to feature.md (#44)

  garrett4wade

  authored
  070a121View commit details

  Copy full SHA for 070a121

  Browse repository at this point

• Update and rename bug-issue-template.md to bug.md (#43)

  garrett4wade

  authored
  f1a9251View commit details

  Copy full SHA for f1a9251

  Browse repository at this point