The Definitive Guide toAI Data Centers
Ask the GuideAboutAccount
GuideGlossaryRollout

Rollout

In reinforcement learning, generating a trajectory of model actions and outcomes used to compute training rewards.

Current numbers

~80%of wall-clock spent on rollout generation in agentic/reasoning RL post-trainingas of 2026 · register ↗
10K–100K+tokens per RL trajectory for reasoning/agentic tasks — the rollout that dominates costas of 2026 · register ↗
~8:1 → ~2:1 and belowGPU:CPU norm rebalancing toward more CPU per node as agentic RL adds rollout/tool/env loadas of 2026 · register ↗

← All terms