Difference between revisions of "Deep Q Network (DQN)"
| Line 14: | Line 14: | ||
* [[Gaming]] | * [[Gaming]] | ||
| − | Deep Q learning, as published in | + | Deep Q learning (DQN), as published in [http://arxiv.org/abs/1312.5602 Playing Atari with Deep Reinforcement Learning | Mnih et al, 2013], leverages advances in deep learning to learn policies from high dimensional sensory input. A convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. [http://towardsdatascience.com/dqn-part-1-vanilla-deep-q-networks-6eb4a00febfb Vanilla Deep Q Networks: Deep Q Learning Explained | Chris Yoon - Towards Data Science] |
Training deep neural networks to show that a novel end-to-end reinforcement learning agent, termed a deep Q-network (DQN) [http://deepmind.com/research/dqn/ Human-level control through Deep Reinforcement Learning | Deepmind] | Training deep neural networks to show that a novel end-to-end reinforcement learning agent, termed a deep Q-network (DQN) [http://deepmind.com/research/dqn/ Human-level control through Deep Reinforcement Learning | Deepmind] | ||
Revision as of 12:31, 1 September 2019
Youtube search... ...Google search
Deep Q learning (DQN), as published in Playing Atari with Deep Reinforcement Learning | Mnih et al, 2013, leverages advances in deep learning to learn policies from high dimensional sensory input. A convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. Vanilla Deep Q Networks: Deep Q Learning Explained | Chris Yoon - Towards Data Science
Training deep neural networks to show that a novel end-to-end reinforcement learning agent, termed a deep Q-network (DQN) Human-level control through Deep Reinforcement Learning | Deepmind
