Does DQN really learn? Exploring adversarial training schemes in Pong.

Bowen He Sreehari Rammohan Jessica Zosa Forde Michael L. Littman

Published in: CoRR (2022)

Keyphrases

test set
neural network
genetic algorithm
training process
efficient learning
real time
social networks
website
web services
multi agent
mobile robot
probabilistic model
evaluation function
training phase
multi layer perceptron