Human-level control through deep reinforcement learning

By Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin A. Riedmiller, A. Fidjeland, Georg Ostrovski and 9 more. 2015

32,431 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Reinforcement Learning

Citations in the corpus

Continuous control with deep reinforcement learning (2015, methodology): “Our contribution in this paper is to provide modifications to DPG, inspired by the success of DQN, which allow it to use neural network function approximators to learn effectively in large state and action spaces online.”
Domain randomization for transferring deep neural networks from simulation to the real world (2017, background): “Learning in simulation is especially promising for building on recent results using deep reinforcement learning to achieve human-level performance on tasks like Atari [27] and robotic control [21], [38].”
Augmented Language Models: a Survey (2023, methodology): “…for learning complex behaviors through feedback-based interaction with an environment, and it has been used for applications such as playing games (Mnih et al., 2015; Silver et al., 2016; Vinyals et al., 2019; Team et al., 2021; Bakhtin et al., 2022) or controlling robots (Gu et al., 2017;…”
Deep Reinforcement Learning from Human Preferences (2017, methodology): “Recent success in scaling reinforcement learning (RL) to large problems has been driven in domains that have a well-speciﬁed reward function (Mnih et al., 2015, 2016; Silver et al., 2016).”
Overcoming catastrophic forgetting in neural networks (2016, background): “These allow action values for each task to be learned off-policy, using an experience replay mechanism (25).”
The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “ould decipher complex sentences like does the shortest thing the tallest pyramid's support supports support anything green? THE NEXT DECADE IN AI / GARY MARCUS 7 much-heralded Atari game system (Mnih et al., 2015) which, as discussed later, succeeded in playing a wide variety of games without a”
Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (2020, background): “The idea of using a slow-moving average target network to produce stable targets for the online network was inspired by deep RL [50, 51, 52, 53].”
Grounded Language Learning in a Simulated 3D World (2017, background): “Recently, however, RL agents controlled by deep neural nets have been trained to solve tasks in both 2D (Mnih et al., 2015) and 3D (Mnih et al., 2016) environments.”
TensorFlow: A system for large-scale machine learning (2016, neutral): “We attribute this success to the invention of more sophisticated machine learning models [42, 51], the availability of large datasets for tack-ling problems in these ﬁelds [10, 65], and the development of software platforms that enable the easy use of large amounts of computational resources for…”
What can the brain teach us about building artificial intelligence? (2016, neutral): “Take the case of the DeepQ network playing ‘breakout’ at a ‘human level’ [5].”
Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks (2018, background): “…(RNN) neural networks have enjoyed great success in many real-world problems, including scene classification Krizhevsky et al., semantic segmentation Papandreou et al. (2015), speech recognition Hinton et al. (2012), gaming Mnih et al. (2013; 2015), and image captioning Johnson et al. (2016).”
Density estimation using Real NVP (2016, background): “This form of batch normalization can be seen as similar to reward normalization in deep reinforcement learning [44, 65].”
Sample Efficient Actor-Critic with Experience Replay (2016, methodology): “The gray curve is the original DQN agent (Mnih et al., 2015) and the black curve is one of the Prioritized Double DQN agents from Schaul et al.”