Train agents to perform better on specific tasks using reinforcement learning. Small models trained on your tasks can outperform larger general models.

​
Overview

HUD integrates with Verifiers for GRPO (Group Relative Policy Optimization) training: 
import verifiers as vf

# Load environment
env = vf.load_environment(
    env_id="hud-vf-gym",
    taskset="hud-evals/2048-taskset",
    config_path="configs/2048.yaml"
)

# Train with GRPO
model, tokenizer = vf.get_model_and_tokenizer("Qwen/Qwen2.5-3B-Instruct")
trainer = vf.GRPOTrainer(
    model=model,
    env=env,
    args=vf.grpo_defaults(),
    peft_config=vf.lora_defaults()  # LoRA for efficiency
)
trainer.train()

​
Why Train?

  • Task Performance: 3B model can reach 80% success vs 35% baseline
  • Cost: Smaller models are cheaper to run
  • Speed: Trained models complete tasks faster
  • Consistency: Less variance in behavior

​
Requirements

​
Monitoring & Analytics

Track training progress in real-time:
  • app.hud.so - View traces, metrics, and rewards for each training generation
  • Weights & Biases - Detailed ML metrics and loss curves
  • Local logs - Training checkpoints and evaluation results

​
Getting Started

RL Quickstart

Train your first agent in 30 minutes

Config System

Configure tools with YAML

Datasets

Create training datasets