From be2d19936546188d6e11831536265988f79ec8a3 Mon Sep 17 00:00:00 2001 From: Chris Wing Date: Tue, 9 Dec 2025 09:40:06 -0800 Subject: [PATCH] Add benefits to About page aligned with README Signed-off-by: Chris Wing --- README.md | 6 +++--- docs/about/index.md | 6 ++++++ 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index bbcf42484..dfdae95ca 100644 --- a/README.md +++ b/README.md @@ -9,9 +9,9 @@ NeMo Gym is a component of the [NVIDIA NeMo Framework](https://docs.nvidia.com/n - Scaffolding and patterns to accelerate environment development: multi-step, multi-turn, and user modeling scenarios - Contribute environments without expert knowledge of the entire RL training loop -- Test environment and throughput end-to-end independent of the RL training loop -- Interoperable with existing environments, systems and RL training frameworks -- Growing collection of training environments and datasets to enable Reinforcement Learning from Verifiable Reward (RLVR) +- Test environments and throughput end-to-end, independent of the RL training loop +- Interoperable with existing environments, systems, and RL training frameworks +- Growing collection of training environments and datasets for Reinforcement Learning from Verifiable Reward (RLVR) > [!IMPORTANT] > NeMo Gym is currently in early development. You should expect evolving APIs, incomplete documentation, and occasional bugs. We welcome contributions and feedback - for any changes, please open an issue first to kick off discussion! diff --git a/docs/about/index.md b/docs/about/index.md index 448f4c9c0..b282ec0ee 100644 --- a/docs/about/index.md +++ b/docs/about/index.md @@ -22,6 +22,12 @@ Embedding custom training environments directly within training frameworks is co [NeMo Gym](https://github.com/NVIDIA-NeMo/Gym) decouples environment development from training, letting you build and iterate on environments independently. It provides the infrastructure to develop agentic training environments and scale rollout collection, enabling seamless integration with your preferred training framework. +- Scaffolding and patterns to accelerate environment development: multi-step, multi-turn, and user modeling scenarios +- Contribute environments without expert knowledge of the entire RL training loop +- Test environments and throughput end-to-end, independent of the RL training loop +- Interoperable with existing environments, systems, and RL training frameworks +- Growing collection of training environments and datasets for Reinforcement Learning from Verifiable Reward (RLVR) + ## Core Components A training environment consists of three server components: