├── .gitignore ├── .gitmodules ├── LICENSE ├── RAGEN.pdf ├── README.md ├── cases ├── reward_hacking.txt └── suck_moment.txt ├── config ├── _1_bandit.yaml ├── _2_sokoban.yaml ├── _3_frozen_lake.yaml ├── _4_countdown.yaml ├── _5_metamathqa.yaml ├── _6_webshop.yaml ├── _7_lean.yaml ├── _8_sudoku.yaml ├── base.yaml ├── envs.yaml ├── eval.yaml ├── eval_webshop.yaml ├── evaluate_api_llm.yaml ├── ppo_trainer.yaml └── stream.yaml ├── public ├── exp1.png ├── exp2.png ├── exp3.png ├── exp4.png ├── exp5.png ├── exp6.png ├── framework.png ├── loss_curve.png ├── ragen.png ├── ragen_logo.jpeg ├── rico.png ├── star-history-202556.png ├── starpo_logo.png ├── step_1.png └── step_2.png ├── pytest.ini ├── ragen ├── __init__.py ├── demo │ ├── __init__.py │ └── run.py ├── env │ ├── __init__.py │ ├── alfworld_old │ │ ├── alfworld_config.yaml │ │ ├── config.py │ │ ├── env.py │ │ └── utils.py │ ├── bandit │ │ ├── __init__.py │ │ ├── config.py │ │ └── env.py │ ├── base.py │ ├── countdown │ │ ├── __init__.py │ │ ├── config.py │ │ └── env.py │ ├── frozen_lake │ │ ├── __init__.py │ │ ├── config.py │ │ ├── env.py │ │ └── utils.py │ ├── lean │ │ ├── __init__.py │ │ ├── config.py │ │ └── env.py │ ├── metamathqa │ │ ├── __init__.py │ │ ├── config.py │ │ └── env.py │ ├── sokoban │ │ ├── __init__.py │ │ ├── config.py │ │ ├── env.py │ │ └── utils.py │ ├── spatial │ │ ├── config.py │ │ ├── env.py │ │ ├── env_old.py │ │ ├── prompter.py │ │ └── prompts.py │ ├── static │ │ ├── config.py │ │ ├── env.py │ │ └── utils.py │ ├── sudoku │ │ ├── __init__.py │ │ ├── config.py │ │ └── env.py │ └── webshop │ │ ├── config.py │ │ └── env.py ├── eval.py ├── eval_api.py ├── llm_agent │ ├── __init__.py │ ├── agent_proxy.py │ ├── ap_webshop.py │ ├── base_llm.py │ ├── ctx_manager.py │ └── es_manager.py ├── patches │ ├── __init__.py │ └── omega_conf_patch.py ├── trainer │ ├── agent_trainer.py │ ├── core_algos.py │ └── rollout_filter.py ├── utils.py └── workers │ ├── __init__.py │ ├── actor │ ├── __init__.py │ └── dp_actor.py │ ├── critic │ ├── __init__.py │ └── dp_critic.py │ ├── fsdp_workers.py │ └── sharding_manager │ ├── base.py │ └── fsdp_vllm.py ├── requirements.txt ├── scripts ├── download_data.py ├── figures │ └── test.ipynb ├── runs │ ├── all_jobs.sh │ ├── bandit_jobs.sh │ ├── frozenlake_jobs.sh │ ├── sokoban_jobs.sh │ ├── webshop_budget_jobs.sh │ ├── webshop_budget_val.sh │ └── webshop_jobs.sh ├── setup_ragen.md ├── setup_ragen.sh ├── setup_ragen_webshop.sh.old ├── setup_webshop.sh └── visualize.py ├── setup.py ├── tests ├── env │ └── test_sokoban_render.py ├── es_manager │ └── test_seed_iteration.py ├── llm_agent │ └── test_context_window.py └── test_rollout_filter.py ├── train.py └── train_all.sh /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/.gitmodules -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/LICENSE -------------------------------------------------------------------------------- /RAGEN.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/RAGEN.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/README.md -------------------------------------------------------------------------------- /cases/reward_hacking.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/cases/reward_hacking.txt -------------------------------------------------------------------------------- /cases/suck_moment.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/cases/suck_moment.txt -------------------------------------------------------------------------------- /config/_1_bandit.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_1_bandit.yaml -------------------------------------------------------------------------------- /config/_2_sokoban.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_2_sokoban.yaml -------------------------------------------------------------------------------- /config/_3_frozen_lake.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_3_frozen_lake.yaml -------------------------------------------------------------------------------- /config/_4_countdown.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_4_countdown.yaml -------------------------------------------------------------------------------- /config/_5_metamathqa.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_5_metamathqa.yaml -------------------------------------------------------------------------------- /config/_6_webshop.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_6_webshop.yaml -------------------------------------------------------------------------------- /config/_7_lean.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_7_lean.yaml -------------------------------------------------------------------------------- /config/_8_sudoku.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/_8_sudoku.yaml -------------------------------------------------------------------------------- /config/base.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/base.yaml -------------------------------------------------------------------------------- /config/envs.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/envs.yaml -------------------------------------------------------------------------------- /config/eval.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/eval.yaml -------------------------------------------------------------------------------- /config/eval_webshop.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/eval_webshop.yaml -------------------------------------------------------------------------------- /config/evaluate_api_llm.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/evaluate_api_llm.yaml -------------------------------------------------------------------------------- /config/ppo_trainer.yaml: -------------------------------------------------------------------------------- 1 | ../verl/verl/trainer/config/ppo_trainer.yaml -------------------------------------------------------------------------------- /config/stream.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/config/stream.yaml -------------------------------------------------------------------------------- /public/exp1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp1.png -------------------------------------------------------------------------------- /public/exp2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp2.png -------------------------------------------------------------------------------- /public/exp3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp3.png -------------------------------------------------------------------------------- /public/exp4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp4.png -------------------------------------------------------------------------------- /public/exp5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp5.png -------------------------------------------------------------------------------- /public/exp6.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/exp6.png -------------------------------------------------------------------------------- /public/framework.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/framework.png -------------------------------------------------------------------------------- /public/loss_curve.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/loss_curve.png -------------------------------------------------------------------------------- /public/ragen.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/ragen.png -------------------------------------------------------------------------------- /public/ragen_logo.jpeg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/ragen_logo.jpeg -------------------------------------------------------------------------------- /public/rico.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/rico.png -------------------------------------------------------------------------------- /public/star-history-202556.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/star-history-202556.png -------------------------------------------------------------------------------- /public/starpo_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/starpo_logo.png -------------------------------------------------------------------------------- /public/step_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/step_1.png -------------------------------------------------------------------------------- /public/step_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/public/step_2.png -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/pytest.ini -------------------------------------------------------------------------------- /ragen/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/__init__.py -------------------------------------------------------------------------------- /ragen/demo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/demo/__init__.py -------------------------------------------------------------------------------- /ragen/demo/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/demo/run.py -------------------------------------------------------------------------------- /ragen/env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/__init__.py -------------------------------------------------------------------------------- /ragen/env/alfworld_old/alfworld_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/alfworld_old/alfworld_config.yaml -------------------------------------------------------------------------------- /ragen/env/alfworld_old/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/alfworld_old/config.py -------------------------------------------------------------------------------- /ragen/env/alfworld_old/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/alfworld_old/env.py -------------------------------------------------------------------------------- /ragen/env/alfworld_old/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/alfworld_old/utils.py -------------------------------------------------------------------------------- /ragen/env/bandit/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/bandit/__init__.py -------------------------------------------------------------------------------- /ragen/env/bandit/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/bandit/config.py -------------------------------------------------------------------------------- /ragen/env/bandit/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/bandit/env.py -------------------------------------------------------------------------------- /ragen/env/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/base.py -------------------------------------------------------------------------------- /ragen/env/countdown/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/countdown/__init__.py -------------------------------------------------------------------------------- /ragen/env/countdown/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/countdown/config.py -------------------------------------------------------------------------------- /ragen/env/countdown/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/countdown/env.py -------------------------------------------------------------------------------- /ragen/env/frozen_lake/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/frozen_lake/__init__.py -------------------------------------------------------------------------------- /ragen/env/frozen_lake/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/frozen_lake/config.py -------------------------------------------------------------------------------- /ragen/env/frozen_lake/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/frozen_lake/env.py -------------------------------------------------------------------------------- /ragen/env/frozen_lake/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/frozen_lake/utils.py -------------------------------------------------------------------------------- /ragen/env/lean/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/lean/__init__.py -------------------------------------------------------------------------------- /ragen/env/lean/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/lean/config.py -------------------------------------------------------------------------------- /ragen/env/lean/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/lean/env.py -------------------------------------------------------------------------------- /ragen/env/metamathqa/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/metamathqa/__init__.py -------------------------------------------------------------------------------- /ragen/env/metamathqa/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/metamathqa/config.py -------------------------------------------------------------------------------- /ragen/env/metamathqa/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/metamathqa/env.py -------------------------------------------------------------------------------- /ragen/env/sokoban/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sokoban/__init__.py -------------------------------------------------------------------------------- /ragen/env/sokoban/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sokoban/config.py -------------------------------------------------------------------------------- /ragen/env/sokoban/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sokoban/env.py -------------------------------------------------------------------------------- /ragen/env/sokoban/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sokoban/utils.py -------------------------------------------------------------------------------- /ragen/env/spatial/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/spatial/config.py -------------------------------------------------------------------------------- /ragen/env/spatial/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/spatial/env.py -------------------------------------------------------------------------------- /ragen/env/spatial/env_old.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/spatial/env_old.py -------------------------------------------------------------------------------- /ragen/env/spatial/prompter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/spatial/prompter.py -------------------------------------------------------------------------------- /ragen/env/spatial/prompts.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/spatial/prompts.py -------------------------------------------------------------------------------- /ragen/env/static/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/static/config.py -------------------------------------------------------------------------------- /ragen/env/static/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/static/env.py -------------------------------------------------------------------------------- /ragen/env/static/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/static/utils.py -------------------------------------------------------------------------------- /ragen/env/sudoku/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sudoku/__init__.py -------------------------------------------------------------------------------- /ragen/env/sudoku/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sudoku/config.py -------------------------------------------------------------------------------- /ragen/env/sudoku/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/sudoku/env.py -------------------------------------------------------------------------------- /ragen/env/webshop/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/webshop/config.py -------------------------------------------------------------------------------- /ragen/env/webshop/env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/env/webshop/env.py -------------------------------------------------------------------------------- /ragen/eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/eval.py -------------------------------------------------------------------------------- /ragen/eval_api.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/eval_api.py -------------------------------------------------------------------------------- /ragen/llm_agent/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /ragen/llm_agent/agent_proxy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/llm_agent/agent_proxy.py -------------------------------------------------------------------------------- /ragen/llm_agent/ap_webshop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/llm_agent/ap_webshop.py -------------------------------------------------------------------------------- /ragen/llm_agent/base_llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/llm_agent/base_llm.py -------------------------------------------------------------------------------- /ragen/llm_agent/ctx_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/llm_agent/ctx_manager.py -------------------------------------------------------------------------------- /ragen/llm_agent/es_manager.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/llm_agent/es_manager.py -------------------------------------------------------------------------------- /ragen/patches/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/patches/__init__.py -------------------------------------------------------------------------------- /ragen/patches/omega_conf_patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/patches/omega_conf_patch.py -------------------------------------------------------------------------------- /ragen/trainer/agent_trainer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/trainer/agent_trainer.py -------------------------------------------------------------------------------- /ragen/trainer/core_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/trainer/core_algos.py -------------------------------------------------------------------------------- /ragen/trainer/rollout_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/trainer/rollout_filter.py -------------------------------------------------------------------------------- /ragen/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/utils.py -------------------------------------------------------------------------------- /ragen/workers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /ragen/workers/actor/__init__.py: -------------------------------------------------------------------------------- 1 | from .dp_actor import DataParallelPPOActor -------------------------------------------------------------------------------- /ragen/workers/actor/dp_actor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/actor/dp_actor.py -------------------------------------------------------------------------------- /ragen/workers/critic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/critic/__init__.py -------------------------------------------------------------------------------- /ragen/workers/critic/dp_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/critic/dp_critic.py -------------------------------------------------------------------------------- /ragen/workers/fsdp_workers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/fsdp_workers.py -------------------------------------------------------------------------------- /ragen/workers/sharding_manager/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/sharding_manager/base.py -------------------------------------------------------------------------------- /ragen/workers/sharding_manager/fsdp_vllm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/ragen/workers/sharding_manager/fsdp_vllm.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/download_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/download_data.py -------------------------------------------------------------------------------- /scripts/figures/test.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/figures/test.ipynb -------------------------------------------------------------------------------- /scripts/runs/all_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/all_jobs.sh -------------------------------------------------------------------------------- /scripts/runs/bandit_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/bandit_jobs.sh -------------------------------------------------------------------------------- /scripts/runs/frozenlake_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/frozenlake_jobs.sh -------------------------------------------------------------------------------- /scripts/runs/sokoban_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/sokoban_jobs.sh -------------------------------------------------------------------------------- /scripts/runs/webshop_budget_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/webshop_budget_jobs.sh -------------------------------------------------------------------------------- /scripts/runs/webshop_budget_val.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/webshop_budget_val.sh -------------------------------------------------------------------------------- /scripts/runs/webshop_jobs.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/runs/webshop_jobs.sh -------------------------------------------------------------------------------- /scripts/setup_ragen.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/setup_ragen.md -------------------------------------------------------------------------------- /scripts/setup_ragen.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/setup_ragen.sh -------------------------------------------------------------------------------- /scripts/setup_ragen_webshop.sh.old: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/setup_ragen_webshop.sh.old -------------------------------------------------------------------------------- /scripts/setup_webshop.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/setup_webshop.sh -------------------------------------------------------------------------------- /scripts/visualize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/scripts/visualize.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/setup.py -------------------------------------------------------------------------------- /tests/env/test_sokoban_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/tests/env/test_sokoban_render.py -------------------------------------------------------------------------------- /tests/es_manager/test_seed_iteration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/tests/es_manager/test_seed_iteration.py -------------------------------------------------------------------------------- /tests/llm_agent/test_context_window.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/tests/llm_agent/test_context_window.py -------------------------------------------------------------------------------- /tests/test_rollout_filter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/tests/test_rollout_filter.py -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/train.py -------------------------------------------------------------------------------- /train_all.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mll-lab-nu/RAGEN/HEAD/train_all.sh --------------------------------------------------------------------------------