RL Glossary
This glossary contains clear and concise definitions of the most important concepts in Reinforcement Learning, organized by categories for easy navigation.
📄️ Agents and Environments
Definitions of agents, environments, states, and actions in Reinforcement Learning.
📄️ RL Algorithms
Definitions and characteristics of the main Reinforcement Learning algorithms.
📄️ Rewards and Policies
How rewards, policies, and value functions work in Reinforcement Learning.
📄️ Exploration vs Exploitation
The fundamental dilemma in Reinforcement Learning between exploring new options and exploiting current knowledge.
📄️ Evaluation and Metrics
How to measure and evaluate the performance of Reinforcement Learning agents.
🎯 How to Use This Glossary
For Beginners
If you're new to RL, we recommend:
- Start with Agents and Environments - Basic concepts
- Explore Algorithms - Learning techniques
- Deepen in Rewards - How learning is guided
For Experienced Developers
If you already have experience:
- Search for specific concepts you need
- Use the index for quick navigation
- Explore connections between concepts
🔍 Quick Search
Basic Concepts
Algorithms
Advanced Concepts
💡 Learning Tips
Use the Glossary Actively
- Don't just read - Search for concepts when you encounter them
- Connect ideas - See how concepts relate to each other
- Practice - Use concepts in real projects
Effective Navigation
- Use the index to find concepts quickly
- Follow links between related concepts
- Come back when you find new terms
🔗 Additional Resources
Theoretical Articles
For more detailed definitions and deep explanations:
- Theoretical Articles - Deep analysis of concepts
Practical Guides
To apply the concepts:
- Getting Started - Set up your environment
- Labs - Practical projects
Can't find a term? Explore our articles for more detailed definitions or read the installation guide to set up your environment.