Dueling Network Architectures for Deep Reinforcement Learning

• DOI: 10.48550/arxiv.1511.06581
• Publication Date: 2015-01-01
• Authors: Ziyu Wang; Tom Schaul; Matteo Hessel; Hado van Hasselt; Marc Lanctot; Nando de Freitas
• Keywords: Factoring; Value network

In recent years there have been many successes of using deep representations in reinforcement learning. Still, these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. this paper, we present a new neural network architecture for model-free Our dueling represents two separate estimators: one the state value function and state-dependent action advantage function. The main benefit factoring is to generalize learning across actions without imposing any change underlying algorithm. results show that leads better policy evaluation presence similar-valued actions. Moreover, enables our RL agent outperform state-of-the-art on Atari 2600 domain.