hf run successfully 0eca069
zhangzf01 commited on
Commit History
add Qwen3-VL (#196) 23ce884 unverified
code adjustment & fix prompt agent bug (#183) 2e24318 unverified
Lang Feng commited on
Add GSPO to verl-agent (#179) 873b913 unverified
Update README and Add FAQ (#173) be05a67 unverified
Lang Feng commited on
Add search-r1 experiments (tool-calling) & the resutls of GiGPO on search-r1 experiments & similarity-based GiGPO (#159) 44be5f4 unverified
Lang Feng commited on
add 'resources_per_worker' config for easily managing cpus/gpus of each env worker (#148) bae6790 unverified
Lang Feng commited on
Add memory manager & Use config in env_manager (#90) cfe3636 unverified
Lang Feng commited on
remove appworld folder and adjust the appworld worker (#80) 37a9e4a unverified
Lang Feng commited on
update LoRA examples (#67) 7595d7b unverified
Lang Feng commited on
update examples (#55) 8d3e6b7 unverified
Lang Feng commited on
Major Update: merge latest verl (#54) 823e1b4 unverified
Lang Feng 湛露先生 
AoShen Franz Srambical 
BaiqingL BearBiscuit HL Blue Space 
tongyx361 Mantas Bakšys Mert Unsal 
yangwang92 Patrik Bartak Junrong Lin BearBiscuit05 
Leege233 
sicer 
wuxibin shengguangming 
wangfuchun-fc 
DuCross Qunhong Zeng Dai, Weinan runluo 
PPPisOK 
hiyouga Haibin Lin 
pengsun000 Hunter Zhang 
Changlong Xiang Long 
zyzshishui 
wangyeyeye zhaochenyang20 
jrlin 
HollowMan6 Tianyun Zhao 
icejieke lixiaoguang12 Earl St Sauver Hongpeng Guo Wang Zhang Wang Zhang Jinn yhyang201 
QQSong Changlong Yu changlyu 
chenhaiquan 
yushengsu Yusheng Su 
none06630663 ShareLer Xiang Long Rihong Qiu Yuhua Jiang 
Swtheking openhands Wei Wu commited on
AoShen Franz Srambical BaiqingL BearBiscuit HL Blue Space tongyx361 Mantas Bakšys Mert Unsal yangwang92 Patrik Bartak Junrong Lin BearBiscuit05 Leege233 sicer wuxibin shengguangming wangfuchun-fc DuCross Qunhong Zeng Dai, Weinan runluo PPPisOK hiyouga Haibin Lin pengsun000 Hunter Zhang Changlong Xiang Long zyzshishui wangyeyeye zhaochenyang20 jrlin HollowMan6 Tianyun Zhao icejieke lixiaoguang12 Earl St Sauver Hongpeng Guo Wang Zhang Wang Zhang Jinn yhyang201 QQSong Changlong Yu changlyu chenhaiquan yushengsu Yusheng Su none06630663 ShareLer Xiang Long Rihong Qiu Yuhua Jiang Swtheking openhands Wei Wu commited on support RLOO 7770564
Update README and scripts, adjust some codes 982ca0c
update README and scripts 789adf0
update scripts and readme ff1753b
upload PPO b82fac5
upload PPO 032542b
fix bugs in gpt4 agents e9096d5
add gpt4o agent eedd710
update scripts e6a85c9
update scripts 5aab662
Achieve unbiased estimate for GiGPO; change the history length of Alfworld to 2 eae9a00
adjust success tags 5f76632
IMPORTANT: achieve two modes of GiGPO: 'mean_std_norm' and 'leave_one_out' 9d6a877
Feng Lang commited on
update script 91bd718
Feng Lang commited on
adjust variable name 6d3c6ea
Feng Lang commited on
avoid potential error in dynamic sampling 18a3a9d
update script beb513c
Feng Lang commited on
update README.md and prompt of ezpoints ffc8872
Feng Lang commited on
adjust script dapo 1852f59
Feng Lang commited on
IMPORTANT: DAPO (https://arxiv.org/abs/2503.14476) support! 85ac871
Feng Lang commited on
adjust webshop script 352bf56
use rule-based reward for webshop 357c592
address issue of info['won'] and update readme and setup file 5401fe7
Feng Lang commited on
IMPORTANT: first implementation of WebShop 671d2f2
Feng Lang commited on
IMPORTANT: achieve the convergence of sokoban and ezpoints 01e15c5
update readme.md b031674
adjust prompt for appworld a77b29f
fix the bug in appworld 13d347e
fix a bug appworld 4a587be
Feng Lang commited on
fix a bug appworld f6db67d
Feng Lang commited on
adjust script for appworld 39e141f
Feng Lang commited on
adjust the prompts for appworld cc14492
Feng Lang commited on
adjust script 65e5e5f
Feng Lang commited on
IMPORTANT: support APPWorld! first version 598d81a
Feng Lang commited on
IMPORTANT: achieve group seeds for gym cards ef3cf2a
add histories for sokoban 6c7461c
IMPORTANT: implementation of sokoban environmetns: support two modality: text and visual 749fe10
Update run_tw.sh 4f651e7 unverified
Lang Feng commited on