photo

James Sorokhaibam


Last seen: 20 jours il y a Actif depuis 2024

Followers: 0   Following: 0

Statistiques

Feeds

Afficher par

Question


High fluctuation in Q0 value for TD3 agent while training.
I am training a TD3 RL agent for pick and place robot. The reward function is, reward = exp(-E/d) where E is the total energy co...

2 mois il y a | 1 réponse | 0

1

réponse