12月1月2月3月4月5月6月7月8月9月10月11月
周一周三周五
一年内 260360 次贡献
更少更多
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xuyang1/fix_denoising_DT 分支9de418989a try to fix denoising
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xuyang1/better_ds_interat_portal 分支d4cccbf693 Refactor code structure for improved readability and maintainability
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xuyang1/add_sample_file_check 分支比较 8 提交 »48ca936c57 move prepare out of global varfa7203330a use sudo to clean workspacefc1c6b7e64 move to CI1de2f2e9ea clear CI workspace before runningb010171cfe simplify
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xuyang1/align_mlebench_data_and_evaluation 分支比较 7 提交 »3b99b457a0 transfer changes of iceberg432d77263d fix error in ventilator tplac2e798d2b fix ci error616343403f add the score of each model in every experimente262a0079d fix bugs
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xiaoyang/add_tpl 分支比较 5 提交 »5ae2ccbe3c Add more details about docker7595513e5c add move to linear model5398eb6c24 feat: new-york-city-taxi-fare-prediction_template2be3f01078 copy init versiond7e211c2b1 several improvement on kaggle loop
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xuyang1/add_coder_check_and_give_more_time 分支eee4686310 Merge branch 'xuyang1/revert_feedback_change' into xuyang1/add_coder_check_and_give_more_time
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 xianbw-fix-merge-auto-recovery-state 分支8321cab98f fix: scope merge auto-recovery state per experiment
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 webshop 分支比较 10 提交 »3785a3eb5c adjust flask dependencycdc83ff420 Add webshop benchmark and update description56fbab3b92 opencode start.sh: restore --max-retries and --eval-timeout for opencode-rl5007063658 opencode start.sh: prepend training env bin to PATH0683730949 opencode start.sh: pass --run-dir to use AutoRL-Bench workspace
- frostbyte_neo 推送了仓库 github-featured/microsoft--rd-agent 的 wanyi/rl_post_training 分支57ac422271 feat: add RL post-training scenario (copied from finetune)
