Community Profile

photo

Matteo Padovani


Last seen: presque 3 ans il y a Actif depuis 2021

Statistiques

  • Thankful Level 2
  • Thankful Level 1

Afficher les badges

Content Feed

Afficher par

Question


How to avoid repeated actions and to manually end episode for a DQN agent?
I'm using the reinforcement learning toolbox to design and train a DQN agent. At each time step the task of the agent is to sele...

environ 3 ans il y a | 1 réponse | 0

1

réponse

Question


How to set DQN network to approach Q0 ?
I'm using the reinforcement learning toolbox to design and train a DQN agent. My action space is a discrete action space compos...

environ 3 ans il y a | 1 réponse | 1

1

réponse

Question


Epsilon greedy algorithm and environment reset do not work during DQN agent training
I'm using the reinforcement learning toolbox to design and train a DQN agent. The action space of the agent is composed by 24 di...

environ 3 ans il y a | 1 réponse | 0

1

réponse