Login / Signup
Reinforcement Learning Based Self-play and State Stacking Techniques for Noisy Air Combat Environment.
Ahmet Semih Tasbas
Safa Onur Sahin
Nazim Kemal Ure
Published in:
CoRR (2023)
Keyphrases
</>
reinforcement learning
air combat
state space
real time
noisy environments
agent receives
supervised learning
state transition
dynamic programming
initially unknown
e learning
neural network
reinforcement learning algorithms
real robot
state transitions
partial knowledge
transition model
robocup soccer