Skip to main content
Synth AI home page
Search...
⌘K
GitHub
Get Started
Get Started
Search...
Navigation
Reinforcement Learning
Reinforcement Learning
Get Started
Cookbooks
Blog
SDK
CLI
Overview
Overview
API Keys
Synth API Key
Environment API Key
Task Apps
Task Apps Overview
In-Process Task App
Standalone Task Apps
Tracing
V3 Trace Format
Rewards
Specs
Jobs
Jobs Overview
Research Agent
Prompt Optimization
Reinforcement Learning
Reinforcement Learning
GSPO
Supervised Fine-Tuning
Reinforcement Learning
Reinforcement Learning
Training models with reinforcement learning
Train models using reinforcement learning with custom reward signals.
GEPA
GSPO
⌘I