 |
 |
 Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient
Estimation for Deep Reinforcement LearningNeural Information Processing Systems (NeurIPS), 2017 |
 Trainable Greedy Decoding for Neural Machine TranslationConference on Empirical Methods in Natural Language Processing (EMNLP), 2017 |
 Sim-to-Real Robot Learning from Pixels with Progressive NetsConference on Robot Learning (CoRL), 2016 |
 Decoupled Neural Interfaces using Synthetic GradientsInternational Conference on Machine Learning (ICML), 2016 |
 High-Dimensional Continuous Control Using Generalized Advantage
EstimationInternational Conference on Learning Representations (ICLR), 2015 |
