When doing reinforcement learning, I have to start training from the beginning each time. It costs lots of time. Is there any solution on starting training from the previous training results? Thanks.
Asked
Active
Viewed 168 times
4
Leo
- 1,273
- 9
- 14
seabiscuit
- 41
- 1
-
Note that there's also [Artificial Intelligence Stack Exchange](https://ai.stackexchange.com/) to ask theoretical questions related to reinforcement learning. – nbro Jul 08 '20 at 21:09
1 Answers
0
If you are doing reinforcement learning based on episodes, you can save the networks you have trained to a file every X episodes. When you are running the script, you can check if that file exists, and load it instead of starting with an empty network.
How you can do this depends on which programming language you're using.
If you are using Python, you can save your data, state table and neural network weights using the Pickle or JSON modules.
Leo
- 1,273
- 9
- 14