Reinforcement Learning Toolbox - Change Action Space
4 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Federico Sello
le 21 Juil 2019
Commenté : Emmanouil Tzorakoleftherakis
le 24 Juil 2019
(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 commentaires
Réponse acceptée
Emmanouil Tzorakoleftherakis
le 23 Juil 2019
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 commentaires
Emmanouil Tzorakoleftherakis
le 24 Juil 2019
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.
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Training and Simulation dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!