Reinforcement Learning Toolbox - Change Action Space
4 次查看(过去 30 天)
显示 更早的评论
Federico Sello
2019-7-21
评论: Emmanouil Tzorakoleftherakis
2019-7-24
(I'm using a DQN Agent in a custom template enviroment)
Is there a way to change the Action Space from which the action is choosen based on the current state during an episode?
For example let's say I have an agent that is moving in a room by choosing the directions of the motion, I would like that when he reaches the edge of the room in one direction he can no longer choose the direction that would eventually lead him off, thus reducing the Action Space.
Basically I want to reduce the Action Space to handle illegal moves.
0 个评论
采纳的回答
Emmanouil Tzorakoleftherakis
2019-7-23
Hi Federico,
Unfortunately, the action space is fixed once created. To reduce the amount of times an action is selected, you could penalize it in the reward signal if certain criteria are met.
I hope this helps.
2 个评论
Emmanouil Tzorakoleftherakis
2019-7-24
In general, DQN has the tendency to choose more frequently optimistically estimated values due to maximization bias. Some additional things that may be helpful:
1) Make sure you are using double dqn (check the dqn agent options) to reduce overestimation
2) Play with the exploration settings. After exploration decays considerably, agent tends to choose what's best according to current values, which may not converge to true values. Decreasing the decay rate may help.
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Training and Simulation 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!