> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/gym/llms.txt. > For full documentation content, see https://docs.nvidia.com/nemo/gym/llms-full.txt. # Training Tutorials We have hands-on tutorials with supported training frameworks to help you train with NeMo Gym environments. If you're interested in integrating another training framework, see the [Training Framework Integration Guide](/latest/contribute/rl-framework-integration). See [Training](/latest/about/concepts/training) for a refresher on when to use GRPO, SFT, or DPO. ## RL (GRPO) Tutorial-series: GRPO training to improve multi-step tool calling on the Workplace Assistant environment, scaling from single-node to multi-node training. nemo rl grpo 3-5 hours Review the agent executor for using NeMo Gym environments with OpenRLHF. openrlhf Example GRPO training on instruction following and reasoning environments. unsloth single-gpu 30 min Example DAPO training on math and agentic environments using VeRL, with single and multi-environment support. verl dapo multi-node 1 hour ### Multi-Environment Training Run multiple training environments simultaneously for rollout collection. multi-environment multi-verifier ## SFT & DPO Transform rollouts into training data for supervised fine-tuning (SFT) and direct preference optimization (DPO). sft dpo