Reinforcement learning unable to dupilcapte the best reward i had during training
1 view (last 30 days)
Show older comments
lab on 24 Aug 2022
Answered: Emmanouil Tzorakoleftherakis on 26 Jan 2023
I use matlab RL toolbox to train a model and I set following rltrainingoptions:
op = rlTraingOptions('StopTrainingCriteria','EpisodeReward','StopTrainingValue',100);
the training process stops when the episodeReawrd>100, however when i used the trained agent to simulate, the episode reward is much lower than 100. Does anybody know why? The other condition is exactly the same.
Emmanouil Tzorakoleftherakis on 26 Jan 2023
Just because the reward of a single episode meets the desired performance, this does not mean that when you stop ttraining you should see exactly the same behavior from the agent. It could be that the agent was influenced by parameters such as exploration, environment noise etc to get to this result.
Before stopping training, you shouldbe able to see consistent good behavior across multiple episodes in a row (or high average episode reward). In that case, after stopping training, the agent behavior should be close to what you saw in training.
Find more on Reinforcement Learning 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!