david-silver

What problem does it solve?

This skill helps you design AI systems that learn from experience rather than relying on human data, enabling agents to discover novel strategies through self-play and environmental interaction.

Core Features & Use Cases

• Applies David Silver's tabula rasa RL philosophy to system design, emphasizing autonomous learning loops, exploration vs. exploitation, and avoidance of hardcoded heuristics.
• Provides key mental models and frameworks (Era of Experience, Cake Recipe, Games as Microcosms, Rising Tide, RL Agent Decomposition, DiscoRL, Dyna-2) to guide RL architecture and project scoping.
• Useful for evaluating learning algorithms, designing RL training loops, and discussing AGI pathways across domains such as games, robotics, and simulations.

Quick Start

Describe a problem and implement a basic RL loop that learns from environment interaction rather than human data.