Customized Action Selection in RL DQN
3 ビュー (過去 30 日間)
古いコメントを表示
Hi,
I would like to ask if the latest Reinforcement Learning (RL) toolbox version supports customized action selection.
I’m currently using a DQN agent, and the action in each time step is selected randomly following the epsilon-greedy algorithm. However, I would like to feed in some probabilities in the action selection, such that certain actions are more likely to be chosen. Is this possible using the RL toolbox?
Thank you!
0 件のコメント
回答 (1 件)
Emmanouil Tzorakoleftherakis
2021 年 1 月 16 日
編集済み: Emmanouil Tzorakoleftherakis
2021 年 1 月 16 日
Hello,
I believe this is not possible yet. A potential workaround (although not state dependent) would be to emulate a pdf by providing actions with higher probabilities multiple times when creating your action space with rlFinitesetSpec but I haven't tested that. So something like:
actInfo = rlFiniteSetSpec([-2 0 2 2 2])
参考
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!