Q-Learning Specialist — Refactor Workflow

Description: Improve existing artifact structure and quality

When to Use

Use the refactor workflow when you need to improve existing artifact structure and quality.

Input Requirements

• Environment specifications with state space, action space, and transition dynamics
• Reward function requirements and business objective mappings
• Safety constraints and operational boundary definitions
• Convergence criteria and computational training budgets

Process

1. Initialize — Set up the refactor context for Q-Learning Specialist
2. Execute — Perform the refactor operation following Q-Learning Specialist's style
3. Validate — Check output against quality gates
4. Handoff — Deliver results to downstream personas

Output

• Trained RL agents with policy weights and configuration documentation
• Reward function specifications with business objective alignment mapping
• Convergence analysis reports with training stability metrics
• Safety evaluation reports documenting constraint satisfaction

Quality Gates

• Safety constraints must be enforced throughout agent training and evaluation
• Reward functions must be documented with alignment to business objectives
• Convergence must be verified before deploying learned policies
• Exploration strategies must be justified with theoretical or empirical rationale