.gitignore
.pre-commit-config.yaml
CITATION.cff
CONTRIBUTING.md
LICENSE
README.md
pyproject.toml
requirements.txt
setup.py
.github/workflows/ci.yml
.github/workflows/conda-publish.yml
.github/workflows/docs-build.yml
.github/workflows/docs.yml
.github/workflows/pre-commit.yml
.github/workflows/pypi-publish.yml
.github/workflows/tests.yml
comlrl/__init__.py
comlrl.egg-info/PKG-INFO
comlrl.egg-info/SOURCES.txt
comlrl.egg-info/dependency_links.txt
comlrl.egg-info/requires.txt
comlrl.egg-info/scm_file_list.json
comlrl.egg-info/scm_version.json
comlrl.egg-info/top_level.txt
comlrl/models/__init__.py
comlrl/models/actor_critic.py
comlrl/schedulers/__init__.py
comlrl/schedulers/device_scheduler.py
comlrl/trainers/__init__.py
comlrl/trainers/actor_critic/__init__.py
comlrl/trainers/actor_critic/ac_base.py
comlrl/trainers/actor_critic/iac.py
comlrl/trainers/actor_critic/maac.py
comlrl/trainers/preference/__init__.py
comlrl/trainers/preference/centralized.py
comlrl/trainers/preference/checkpointing.py
comlrl/trainers/preference/collaboration.py
comlrl/trainers/preference/iterative.py
comlrl/trainers/preference/madpo.py
comlrl/trainers/preference/marlhf.py
comlrl/trainers/preference/output_paths.py
comlrl/trainers/reinforce/__init__.py
comlrl/trainers/reinforce/centralized_magrpo.py
comlrl/trainers/reinforce/magrpo.py
comlrl/trainers/reinforce/mareinforce.py
comlrl/trainers/reinforce/maremax.py
comlrl/trainers/reinforce/marloo.py
comlrl/utils/__init__.py
comlrl/utils/checkpoint.py
comlrl/utils/distributed.py
comlrl/utils/formatters.py
comlrl/utils/model_loading.py
comlrl/utils/reference_kl.py
comlrl/utils/reward_processor.py
comlrl/utils/reward_utils.py
comlrl/utils/tokenizer_utils.py
comlrl/utils/wandb_utils.py
docs/.gitignore
docs/README.md
docs/go.mod
docs/go.sum
docs/hugo.toml
docs/assets/_algorithm-flows.scss
docs/assets/_custom.scss
docs/assets/_diagram-theme.scss
docs/assets/_language.scss
docs/assets/_syntax.scss
docs/assets/_theme.scss
docs/assets/_variables.scss
docs/assets/comlrl.png
docs/assets/demo.gif
docs/assets/docs.js
docs/assets/email.svg
docs/assets/katex.json
docs/assets/rollout-diagrams.js
docs/assets/sponsors.png
docs/assets/theme.js
docs/assets/visual-viewer.js
docs/assets/rollouts/ac-training.svg
docs/assets/rollouts/ac.svg
docs/assets/rollouts/align-tree.svg
docs/assets/rollouts/comparator-pairs.svg
docs/assets/rollouts/cross-tree.svg
docs/assets/rollouts/environment-transition.svg
docs/assets/rollouts/joint-tree.svg
docs/assets/rollouts/madpo-training.svg
docs/assets/rollouts/mapl-iterative.svg
docs/assets/rollouts/marlhf-training.svg
docs/assets/rollouts/reinforce-baselines.svg
docs/assets/rollouts/reinforce-training.svg
docs/assets/rollouts/replay-modes.svg
docs/content/_index.md
docs/content/docs/dev/_index.md
docs/content/docs/dev/changelog.md
docs/content/docs/dev/contributing.md
docs/content/docs/dev/support.md
docs/content/docs/env/_index.md
docs/content/docs/env/bfcl.md
docs/content/docs/env/code-completion.md
docs/content/docs/env/coding.md
docs/content/docs/env/minecraft.md
docs/content/docs/env/travel.md
docs/content/docs/env/writing.md
docs/content/docs/examples/_index.md
docs/content/docs/examples/advanced/_index.md
docs/content/docs/examples/advanced/multi-turn-feedback.md
docs/content/docs/examples/advanced/resume-training.md
docs/content/docs/examples/quick-start/_index.md
docs/content/docs/examples/quick-start/length-ratio-training.md
docs/content/docs/marl/_index.md
docs/content/docs/marl/multi-agent-actor-critic.md
docs/content/docs/marl/multi-agent-reinforce.md
docs/content/docs/marl/multi-llm-pbrl.md
docs/content/docs/marl/multi-turn-interaction.md
docs/content/docs/research/_index.md
docs/content/docs/user-guide/_index.md
docs/content/docs/user-guide/installation.md
docs/content/docs/user-guide/qa.md
docs/content/docs/user-guide/training-entities.md
docs/content/docs/user-guide/training-initialization.md
docs/content/docs/user-guide/training-parallelization.md
docs/data/languages.json
docs/i18n/de.toml
docs/i18n/en.toml
docs/i18n/es.toml
docs/i18n/fr.toml
docs/i18n/ja.toml
docs/i18n/ko.toml
docs/i18n/zh-cn.toml
docs/layouts/alias.html
docs/layouts/baseof.html
docs/layouts/_partials/docs/copyright.html
docs/layouts/_partials/docs/header.html
docs/layouts/_partials/docs/language-switcher.html
docs/layouts/_partials/docs/menu.html
docs/layouts/_partials/docs/nav-area.html
docs/layouts/_partials/docs/nav-icon.html
docs/layouts/_partials/docs/nav-link.html
docs/layouts/_partials/docs/navigation.html
docs/layouts/_partials/docs/openmlrl-icon.html
docs/layouts/_partials/docs/prev-next.html
docs/layouts/_partials/docs/site-header.html
docs/layouts/_partials/docs/toc.html
docs/layouts/_partials/docs/inject/content-before.html
docs/layouts/_partials/docs/inject/head.html
docs/layouts/_shortcodes/hint.html
docs/layouts/_shortcodes/katex.html
docs/layouts/_shortcodes/publication.html
docs/layouts/_shortcodes/relurl.html
docs/layouts/_shortcodes/resource-card.html
docs/layouts/_shortcodes/rollout-diagram.html
docs/scripts/ac-training.tex
docs/scripts/build.py
docs/scripts/check_html.py
docs/scripts/check_translations.py
docs/scripts/environment-transition.tex
docs/scripts/prepare_demo_animation.py
docs/scripts/prepare_rollout_svgs.py
docs/scripts/preview.py
docs/scripts/reinforce-baselines.tex
docs/scripts/reinforce-training.tex
docs/scripts/translations.py
docs/static/fonts/Inter-LICENSE.txt
docs/static/fonts/InterVariable-Italic.woff2
docs/static/fonts/InterVariable.woff2
docs/static/img/ac-training.svg
docs/static/img/ac.svg
docs/static/img/align-tree.svg
docs/static/img/comlrl-icon.png
docs/static/img/comlrl-icon.svg
docs/static/img/comlrl-logo-dark-colors.svg
docs/static/img/comlrl-logo-reading-colors.svg
docs/static/img/comlrl-logo.png
docs/static/img/cross-tree.svg
docs/static/img/demo-hd.webp
docs/static/img/environment-transition.svg
docs/static/img/joint-tree.svg
docs/static/img/reinforce-baselines.svg
docs/static/img/reinforce-training.svg
examples/leetcode-func-print.py
examples/story-len-ratio.py
examples/tldr-len-ratio.py
tests/checkpoint_helpers.py
tests/conftest.py
tests/helpers.py
tests/test_actor_critic.py
tests/test_centralized_comparator.py
tests/test_centralized_magrpo.py
tests/test_centralized_preference.py
tests/test_checkpoint_assets.py
tests/test_checkpoint_files.py
tests/test_checkpoint_metadata.py
tests/test_checkpoint_models.py
tests/test_checkpoint_nested.py
tests/test_checkpoint_preference.py
tests/test_checkpoint_preference_specials.py
tests/test_checkpoint_rl.py
tests/test_checkpoint_rng.py
tests/test_checkpoint_state.py
tests/test_checkpoint_tokenizer_specials.py
tests/test_config.py
tests/test_joint_policy.py
tests/test_magrpo.py
tests/test_parallel_agent_tasks.py
tests/test_preference.py
tests/test_reference_kl.py
tests/test_trainer_init.py
tests/test_utils.py