Sign in
Score vs. Winrate in Score-Based Games: which Reward for Reinforcement Learning?
Luca Pasqualini
Maurizio Parton
Francesco Morandin
Gianluca Amato
Rosa Gini
Carlo Metta
Marco Fantozzi
Alessandro Marchetti
Published in:
ICMLA (2022)
Keyphrases
</>
reinforcement learning
dynamic programming
machine learning
function approximation
multi agent
state space
markov decision processes
game theory
educational games
game theoretic
reinforcement learning algorithms
action sets