Augmented Q Imitation Learning (AQIL)
This addresses the problem of training time for researchers and practitioners in reinforcement learning, but it appears incremental as it builds on existing methods.
The paper tackles slow convergence in deep reinforcement learning by introducing Augmented Q-Imitation Learning, which uses Q-imitation learning as an initial training step to accelerate convergence in Deep Q-learning, though no concrete numbers are provided.
The study of unsupervised learning can be generally divided into two categories: imitation learning and reinforcement learning. In imitation learning the machine learns by mimicking the behavior of an expert system whereas in reinforcement learning the machine learns via direct environment feedback. Traditional deep reinforcement learning takes a significant time before the machine starts to converge to an optimal policy. This paper proposes Augmented Q-Imitation-Learning, a method by which deep reinforcement learning convergence can be accelerated by applying Q-imitation-learning as the initial training process in traditional Deep Q-learning.