Reinforcement Learning Toolbox - Change Action Space
3 views (last 30 days)
Show older comments
Federico Sello
on 21 Jul 2019
Commented: Emmanouil Tzorakoleftherakis
on 24 Jul 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 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 23 Jul 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 Comments
Emmanouil Tzorakoleftherakis
on 24 Jul 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.
More Answers (0)
See Also
Categories
Find more on Training and Simulation 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!