Determine the reward value to stop training in RL agent
4 views (last 30 days)
Show older comments
H. M.
on 17 Oct 2022
Commented: Francisco Serra
on 14 Dec 2023
I saw in example of using RL agent, this sentence:
- Stop training when the agent receives an average cumulative reward greater than -355 over 100 consecutive episodes. At this point, the agent can control the level of water in the tank.
how did he calculate the exact reward -355 over 100 episodes? Is there any tips could help know when to stop the training at specific point before get worst.
thank you advance
0 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 25 Jan 2023
Edited: Emmanouil Tzorakoleftherakis
on 25 Jan 2023
For some problems you may be able to calculate what the maximum reward that can be collected in an episode is, so you can use this knowledge accordingly in the training settings. In general, there is no recipe that will tell you when it would be good to stop training. You would typically need to train for a large number of episodes to see how the training goes and that could help you identify what a good average reward is. You could also just train for a set number of episodes instead (similar to how you would train for a certain number of epochs in supervised learning).
Hope that helps
0 Comments
More Answers (1)
Sam Chak
on 17 Oct 2022
2 Comments
Francisco Serra
on 14 Dec 2023
For example, imagine your are using a RL agent for a control problem. You can use a classic controller to have a reference and apply to it the same cost function you use in the RL Agent. Then you do some simulations with that controller, you see how it goes and then you have an idea of how your RL Agent should perform. However, if you don't have a working reference to guide yourself you have to do what @Emmanouil Tzorakoleftherakis said.
See Also
Categories
Find more on Training and Simulation in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!