Reinforcement learning in DataRobot¶
In this accelerator, you implement a very simple model based on the Q-learning algorithm. This accelerator shows a basic form of reinforcement learning that doesn't require a deep understanding of neural networks or advanced mathematics and how one might deploy such a model in DataRobot.
This example shows the Grid World problem, where an agent learns to navigate a grid to reach a goal.
The accelerator will go through the following steps:
- Define state and action space
- Create a Q-table to store expected rewards for each state/action combination
- Implement a learning algorithm and train a model
- Evaluate the model
- Deploy the model to a DataRobot REST API endpoint
更新しました June 7, 2024
このページは役に立ちましたか?
ありがとうございます。どのような点が役に立ちましたか?
より良いコンテンツを提供するには、どうすればよいでしょうか?
アンケートにご協力いただき、ありがとうございました。