- Trust Region Policy Optimization [arXiv]
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning [arXiv]
- Continuous Deep Q-Learning with Model-based Acceleration [arXiv]
- Asynchronous Methods for Deep Reinforcement Learning [arXiv]
- Dueling Network Architectures for Deep Reinforcement Learning - ICML'16 Best Paper Award [arXiv]
- Deep Reinforcement Learning with Double Q-learning [arXiv]
- Monte Carlo Bayesian Reinforcement Learning [arXiV]
- Control of Memory, Active Perception, and Action in Minecraft [arXiV]
- Deep Multiagent Reinforcement Learning for Partially Observable Parameterized Environments [arXiv]
- Deep Compression - ICLR'16 Best Paper Award [arXiv]
- Quoc Le's Tutorials on Deep Learning [Tutorial1] [Tutorial2]
- Sequence to Sequence Learning with Neural Networks[arXiv]
- Continuous Control with Deep Reinforcement Learning [arXiv]
- Playing Atari with Deep Reinforcement Learning [arXiv]
- Deep Reinforcement Learning With an Action Space Defined by Natural Language [arXiv]
- WebNav : A New Large-Scale Task for Natural Language based Sequential Decision Making [arXiv]
- Using Reinforcement Learning to Spider the Web Efficiently [ACM]
- Focused Crawling using Temporal Difference Learning [Springer]
- LINE: Large-scale Information Network Embedding
- PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks
- Co-Author Relationship Prediction in Heterogeneous Bibliographic Networks [link]
- Visual Question Answering(VQA) [arXiv]