Community Profile

photo

Cecilia S.


Last seen: ungefär 2 månader ago Active since 2021

Statistics

  • Thankful Level 2
  • Thankful Level 1

View badges

Content Feed

View by

Question


Why does rlQValueRepresentation always add a Regression Output (RepresentationLoss) layer to the end of the network?
I have noticed that if I create a critic using rlQValueRepresentation it includes a Regression Output (named RepresentationLoss)...

ungefär ett år ago | 0 answers | 0

0

answers

Question


Could I learn from past data INCLUDING actions? Could I make vector with actions to be used in a certain order?
If I have a complete set of past data (observations) and a list of the actions taken by some agent (or human), could I update my...

ungefär ett år ago | 1 answer | 1

1

answer

Question


I believe the RL environment template creator has an error in the reset function but I'm not sure
when using rlCreateEnvTemplate("MyEnvironment") to create a custom template I came across this line in the reset function: % Li...

ungefär ett år ago | 1 answer | 0

1

answer

Question


What exactly is Episode Q0? What information is it giving?
Reading documentation I find that "For agents with a critic, Episode Q0 is the estimate of the discounted long-term reward at th...

ungefär ett år ago | 1 answer | 0

1

answer

Question


Resume training of a DQN agent. How to avoid Epsilon from being reset to max value?
When I want to resume training of an agent, I simply load it and set the "resetexperiencebuffer" option to false, but this does ...

ungefär ett år ago | 1 answer | 0

1

answer

Question


Reinforcement Learning Toolbox: Episode Q0 stopped predicting after a few thousand simulations. DQN Agent.
Q0 values were pretty ok until episode 2360, it's not stuck, just increasing very very slowly I'm using the default generated D...

ungefär ett år ago | 0 answers | 0

0

answers