Reinforcement Learning Tool Box : How to change epsilon during training?
3 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Keita Sugiura
el 1 de Oct. de 2019
Respondida: Emmanouil Tzorakoleftherakis
el 4 de Oct. de 2019
I just started using reinforcement learning tool box on matlab.
I have a question in terms of epsilon-greedy settings. Is it possible to change the value of epsilon during training?
For instance, for the firtst 30 episodes, I'd like to set Epsilon = 1 and EpsilonDecay = 0.1. Then, after the first 30 episodes, I'd like to change Epsilon = 0.5 and EpsilonDecay =0.05.
I'd really appreciate your comments and advices. Thanks
0 comentarios
Respuestas (1)
Emmanouil Tzorakoleftherakis
el 4 de Oct. de 2019
Hi Keita,
Have a look at this link. The 'EpsilonGreedyExploration' option provides a way to reduce exploration as training progresses using the formula Epsilon = Epsilon*(1-EpsilonDecay).
We are working on adding more ways to set up the exploration strategy.
0 comentarios
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!