ACtuAL: Actor-Critic Under Adversarial Learning.

Anirudh Goyal Nan Rosemary Ke Alex Lamb R. Devon Hjelm Chris Pal Joelle Pineau Yoshua Bengio

Published in: CoRR (2017)

Keyphrases

actor critic
learning process
neural network
reinforcement learning
learning algorithm
supervised learning
policy gradient methods
linear programming
dynamic environments
markov decision processes
learning tasks