Reinforcement Learning mit Python

Expertenseminar Reinforcement Learning

RL Basics

• Introduction to Reinforcement Learning
• Key concepts: environment, agent, states, rewards
• Value-based, Policy-based, and Model-based Approaches

Q-Learning

• Introduction to Q-Learning
• Q-Table and Bellman Equation
• Implementing Q-Learning
• Simulating a simple environment

Neural Networks

• Basics of neural networks
• Role of neural networks in RL

DQ-Learning

• Introduction to Deep Q-Learning
• Differences between Q-Learning and DQ-Learning
• Implementing Deep Q-Learning

Other RL Methods

• Policy Gradients
• Actor-Critic
• Monte Carlo Methods
• Temporal-Difference Learning

Q&A and Conclusion

 Eingesetzte Tools:

• Python, OpenAI Gym
• Keras und Tensorflow