Methods

Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation ICML 2019 Randomized Adversarial Imitation Learning for Autonomous Driving IJCAI 2019 Randomized Value Functions via Multiplicative Normalizing Flows UAI 2019 Random Projection in Neural Episodic Control ACML 2019 Reading Like HER: Human Reading Inspired Extractive Summarization EMNLP 2019 Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos AAAI 2019 Real-time tree search with pessimistic scenarios: Winning the NeurIPS 2018 Pommerman Competition ACML 2019 Recall Traces: Backtracking Models for Efficient Reinforcement Learning ICLR 2019 Receding Horizon Curiosity CoRL 2019 Recent Advances in Imitation Learning from Observation IJCAI 2019 Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue EMNLP 2019 Reconciling λ-Returns with Experience Replay NeurIPS 2019 Recurrent Existence Determination Through Policy Optimization IJCAI 2019 Recurrent Experience Replay in Distributed Reinforcement Learning ICLR 2019 Regret Bounds for Learning State Representations in Reinforcement Learning NeurIPS 2019 Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function NeurIPS 2019 Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives NeurIPS 2019 Regularized Anderson Acceleration for Off-Policy Deep Reinforcement Learning NeurIPS 2019 Regularizing Model-Based Planning with Energy-Based Models CoRL 2019 Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation CVPR 2019 Reinforced Negative Sampling for Recommendation with Exposure Data IJCAI 2019 Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews EMNLP 2019 Reinforcement Learning based Curriculum Optimization for Neural Machine Translation NAACL 2019 Reinforcement Learning Experience Reuse with Policy Residual Representation IJCAI 2019 Reinforcement Learning in Configurable Continuous Environments ICML 2019