Implementing an epsilon decay schedule

We can decay (or decrease) the value linearly (in the following left-hand side graph), exponentially (in the following right-hand side graph) or using some other decay schedule. Linear and exponential schedules are the most commonly used decay schedules for the exploration parameter :

In the preceding graphs, you can see how the epsilon (exploration) value varies with the different schedule schemes (linear ...

Get Hands-On Intelligent Agents with OpenAI Gym now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.