RL4LMs Logo
latest

Getting Started

  • Installation
  • Quick Start - Train PPO/NLPO using pre-defined YAML configs
  • Custom Building Blocks

Module Guide

  • rl4lms.algorithms package
  • rl4lms.envs package
    • Subpackages
      • rl4lms.envs.common package
      • rl4lms.envs.text_generation package
    • Module contents
  • rl4lms.core_components package
  • rl4lms.data_pools package
RL4LMs
  • rl4lms.envs package
  • Edit on GitHub

rl4lms.envs package

Subpackages

  • rl4lms.envs.common package
    • Submodules
    • rl4lms.envs.common.action_space module
    • rl4lms.envs.common.base_env module
    • rl4lms.envs.common.observation module
    • rl4lms.envs.common.reward module
    • Module contents
  • rl4lms.envs.text_generation package
    • Subpackages
    • Submodules
    • rl4lms.envs.text_generation.alg_wrappers module
    • rl4lms.envs.text_generation.env module
    • rl4lms.envs.text_generation.evaluation_utils module
    • rl4lms.envs.text_generation.hf_generation_utils module
    • rl4lms.envs.text_generation.kl_controllers module
    • rl4lms.envs.text_generation.logging_utils module
    • rl4lms.envs.text_generation.metric module
    • rl4lms.envs.text_generation.observation module
    • rl4lms.envs.text_generation.policy module
    • rl4lms.envs.text_generation.post_processors module
    • rl4lms.envs.text_generation.preference_reward module
    • rl4lms.envs.text_generation.registry module
    • rl4lms.envs.text_generation.reward module
    • rl4lms.envs.text_generation.test_datapool module
    • rl4lms.envs.text_generation.test_metric module
    • rl4lms.envs.text_generation.test_reward module
    • rl4lms.envs.text_generation.training_utils module
    • rl4lms.envs.text_generation.utils_supervised module
    • rl4lms.envs.text_generation.warm_start module
    • Module contents

Module contents

Previous Next

© Copyright 2023, RL4LMs Team. Revision 56f367e7.

Built with Sphinx using a theme provided by Read the Docs.