- Introduction
- A primer on Reinforcement Learning
2.1 Key concepts
2.2 Q-function
2.3 Q-value
2.4 Q-Learning
2.5 The Bellman equation
2.6 Exploration vs. exploitation
2.7 Q-Table - The Dynamic Pricing problem
3.1 Problem statement
3.2 Implementation - Conclusions
- References
On this submit, we introduce the core ideas of Reinforcement Studying and dive into Q-Studying, an method that empowers clever brokers to study optimum insurance policies by making knowledgeable choices based mostly on rewards and experiences.
We additionally share a sensible Python instance constructed from the bottom up. Particularly, we prepare an agent to grasp the artwork of pricing, an important side of enterprise, in order that it could possibly discover ways to maximize revenue.
With out additional ado, allow us to start our journey.
2.1 Key ideas
Reinforcement Studying (RL) is an space of Machine Studying the place an agent learns to perform a process by trial and error.
In short, the agent tries actions that are related to a optimistic or detrimental suggestions by a reward mechanism. The agent adjusts its conduct to maximise a reward, thus studying one of the best plan of action to realize the ultimate objective.
Allow us to introduce the important thing ideas of RL by a sensible instance. Think about a simplified arcade sport, the place a cat ought to navigate a maze to gather treasures — a glass of milk and a ball of yarn — whereas avoiding building websites:
- The agent is the one selecting the course of actions. Within the instance, the agent is the participant who controls the joystick deciding the following transfer of the cat.
- The setting is the…