Understanding Concepts for NeMo Gym#

NeMo Gym concepts explain the mental model behind building reliable agent systems: how services collaborate, how teams capture interaction data, and how verification signals drive learning. Use this page as a compass to decide which explanation to read next.

Tip

Need a refresher on reinforcement learning language? Refer to the Key Terminology before diving in.

How to Navigate This Section#

  • Read these explanations when your team needs shared vocabulary for configuring Models, Resources, and Agents together.

  • Pair each concept page with its related tutorials when you are ready to practice tasks such as assembling interaction datasets or scoring agent behavior.

  • Return here whenever you add a new teammate so that they can orient and choose the depth that fits their role.

Concept Highlights#

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

Core Abstractions

Understand how Models, Resources, and Agents remain decoupled yet coordinated as independent HTTP services, including which endpoints each abstraction exposes.

Core Abstractions
Configuration System

Learn how NeMo Gym’s three-tier configuration system (YAML → env.yaml → CLI) enables secure secrets management and flexible multi-environment deployments.

Configuration Management
Task Verification

Explore how resource servers score agent outputs with verify() implementations that transform correctness, quality, and efficiency checks into reward signals.

Task verification
Key Terminology

Essential vocabulary for agent training, RL workflows, and NeMo Gym. This glossary defines terms you’ll encounter throughout the tutorials and documentation.

Key Terminology