Determine the reward value to stop training in RL agent
4 ビュー (過去 30 日間)
古いコメントを表示
H. M.
2022 年 10 月 17 日
コメント済み: Francisco Serra
2023 年 12 月 14 日
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 件のコメント
採用された回答
Emmanouil Tzorakoleftherakis
2023 年 1 月 25 日
編集済み: Emmanouil Tzorakoleftherakis
2023 年 1 月 25 日
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 件のコメント
その他の回答 (1 件)
Sam Chak
2022 年 10 月 17 日
2 件のコメント
Francisco Serra
2023 年 12 月 14 日
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.
参考
カテゴリ
Help Center および File Exchange で Training and Simulation についてさらに検索
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!