Login / Signup

Exploiting Partial Observability and Optimized Simple State Representations in Deep Q-Learning.

Danyaal MahmoodUsama ArshadRaja Hashim AliZain Ul AbideenMuhammad Huzaifa ShahTalha Ali KhanAli Zeeshan IjazNisar AliAbu Bakar Siddique
Published in: FIT (2023)
Keyphrases
  • partial observability
  • reinforcement learning
  • partially observable
  • learning algorithm
  • multi agent
  • cooperative
  • optimal policy
  • neural network
  • belief state