International Conference on Machine Learning · 2017 · 30 citations · 15 references
ComputingComputer SciencePhysicsArtificial IntelligenceCausal InferenceMachine LearningAction RepresentationDeep LearningNeural NetworksReinforcement LearningReinforcement Learning FoundationsTransfer LearningCausal ReasoningCausal RelationshipsData GeneralizationDeep Reinforcement LearningProgressive Neural NetworksTask TransferTrainingTransferable Representation Learning
The recent adaptation of deep neural network-based methods to reinforcement learning and planning domains has yielded remarkable progress on individual tasks. Nonetheless, progress on task-to-task transfer remains limited. In pursuit of efficient and robust generalization, we introduce the Schema Network, an object-oriented generative physics simulator capable of disentangling multiple causes of events and reasoning backward through causes to achieve goals. The richly structured architecture of the Schema Network can learn the dynamics of an environment directly from data. We compare Schema Networks with Asynchronous Advantage Actor-Critic and Progressive Networks on a suite of Breakout variations, reporting results on training efficiency and zero-shot generalization, consistently demonstrating faster, more robust learning and better transfer. We argue that generalizing from limited data and learning causal relationships are essential abilities on the path toward generally intelligent systems.
15
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations
Interaction Networks for Learning about Objects, Relations and Physics
Peter Battaglia, Razvan Pascanu, Matthew Lai et al. · arXiv (Cornell University) · 2016 · 577 citations · Full text
Computing, Computer Science, Physics +13