> 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 AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/gym/_mcp/server.

# Concepts

NeMo Gym concepts explain the mental model behind building RL training environments: when to use RL over SFT, how environment components work together, and how verification signals drive learning. Use this page as a compass to decide which explanation to read next.

New to RL for LLMs? Start with [training-approaches](/v0.2/about/concepts/training-approaches) for context on SFT, RL, and RLVR, or refer to [Key Terminology](/v0.2/about/concepts/key-terminology) for a quick glossary.

---

## Concept Highlights

Each explainer below covers one foundational idea and links to deeper material.

#### [Training Approaches](/v0.2/about/concepts/training-approaches)

Understand the differences between SFT, DPO, and GRPO, and the rise of RLVR.

#### [Environment Components](/v0.2/about/concepts/core-components)

Understand the three server components that make up a training environment.

#### [Configuration System](/v0.2/about/concepts/configuration)

Understand how servers are configured and connected.

#### [Architecture](/v0.2/about/concepts/architecture)

How components interact during startup and rollout collection.

#### [Task Verification](/v0.2/about/concepts/task-verification)

Understand the importance of verification and common implementation patterns.

#### [Key Terminology](/v0.2/about/concepts/key-terminology)

Essential vocabulary for agent training, RL workflows, and NeMo Gym.

---