DQN Paper
Human-level control through deep reinforcement learning
This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Deep Q-network (DQN)
- Combine reinforcement learning with deep neural networks.
- Deep convolutional network
- which uses hierarchical layers of tiled convolutional filters to mimic the effects of receptive fields—inspired by Hubel and Wiesel’s seminal work on feedforward processing in early visual cortex
- thereby exploiting the local spatial correlations present in images
- and building in robustness to natural transformations such as changes of viewpoint or scale.
Ref
- Mnih, Volodymyr, et al. “Human-level control through deep reinforcement learning” Nature518.7540 (2015): 529.