Human-level control through deep reinforcement learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, +16

Nature

Artificial IntelligenceEngineeringDeep Reinforcement LearningReinforcement Learning (Educational Psychology)Computer Science +1

Overcoming catastrophic forgetting in neural networks

James Kirkpatrick, Razvan Pascanu, Neil C. Rabinowitz, +11

Proceedings of the National Academy of Sciences

Artificial IntelligenceLearning ProblemCognitive ScienceEngineeringMachine Learning +13

Progressive Neural Networks

Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, +5

arXiv (Cornell University)

Artificial IntelligenceIncremental LearningEngineeringMachine LearningSequential Learning +17

PathNet: Evolution Channels Gradient Descent in Super Neural Networks

Chrisantha Fernando, Dylan Banarse, Charles Blundell, +5

arXiv (Cornell University)

Artificial IntelligenceModel OptimizationEvolving Neural NetworkEngineeringMachine Learning +10

Neural scene representation and rendering

S. M. Ali Eslami, Danilo Jimenez Rezende, Frederic Besse, +19

Science

EngineeringMachine LearningScene Representation-the ProcessRepresentation LearningImage Analysis +15

Imagine All the People: How the Brain Creates and Uses Personality Models to Predict Behavior

Demis Hassabis, R. Nathan Spreng, Andrei A. Rusu, +3

Cerebral Cortex

NeuropsychologyPredict BehaviorAffective NeuroscienceBrain CreatesBehavior Prediction +16

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Yuke Zhu, Ziyu Wang, Josh Merel, +8

Meta-Learning with Latent Embedding Optimization

Andrei A. Rusu, Dushyant Rao, Jakub Sygnowski, +4

arXiv (Cornell University)

Artificial IntelligenceFew-shot LearningGradient-based Meta-learningModel OptimizationEngineering +13

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

Irina Higgins, Arka Pal, Andrei A. Rusu, +5

arXiv (Cornell University)

Artificial IntelligenceFew-shot LearningEngineeringMachine LearningData Science +6

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Yuke Zhu, Ziyu Wang, Josh Merel, +8

arXiv (Cornell University)

Artificial IntelligenceMotor LearningEngineeringMachine LearningModel-free Deep Reinforcement +18