Dueling Network Architectures for Deep Reinforcement LearningIn recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state
AIで株をやる！～株の売り買いを深層強化学習で予想 - Speaker Deck
