Robust Dual View Deep Agent
arXiv:1804.05120
Abstract
Motivated by recent advance of machine learning using Deep Reinforcement Learning this paper proposes a modified architecture that produces more robust agents and speeds up the training process. Our architecture is based on Asynchronous Advantage Actor-Critic (A3C) algorithm where the total input dimensionality is halved by dividing the input into two independent streams. We use ViZDoom, 3D world software that is based on the classical first person shooter video game, Doom, as a test case. The experiments show that in comparison to single input agents, the proposed architecture succeeds to have the same playing performance and shows more robust behavior, achieving significant reduction in the number of training parameters of almost 30%.
arXiv commentProceeding of the 2nd International Sino-Egyptian Congress on Agriculture, Veterinary Sciences and Engineering, 7-10 October 2017
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Playing Atari with Deep Reinforcement Learning
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Dueling Network Architectures for Deep Reinforcement Learning
- Continuous Inverse Optimal Control with Locally Optimal Examples