Deep RL

Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting NeurIPS 2021 Sample Efficient Reinforcement Learning with REINFORCE AAAI 2021 Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing ICML 2021 SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II ICML 2021 SEAGuL: Sample Efficient Adversarially Guided Learning of Value Functions L4DC 2021 Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs ACL 2021 Self-correcting Q-learning AAAI 2021 Self-Supervised Attention-Aware Reinforcement Learning AAAI 2021 Self-supervised Visual Reinforcement Learning with Object-centric Representations ICLR 2021 SENSEI: Aligning Video Streaming Quality with Dynamic User Sensitivity NSDI 2021 Sequential Generative Exploration Model for Partially Observable Reinforcement Learning AAAI 2021 Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks ICML 2021 SimPoE: Simulated Character Control for 3D Human Pose Estimation CVPR 2021 Skill Discovery for Exploration and Planning using Deep Skill Graphs ICML 2021 SMiRL: Surprise Minimizing Reinforcement Learning in Unstable Environments ICLR 2021 Smooth Exploration for Robotic Reinforcement Learning CoRL 2021 Solving Compositional Reinforcement Learning Problems via Task Reduction ICLR 2021 Solving Continuous Control with Episodic Memory IJCAI 2021 Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play IJCAI 2021 SOON: Scenario Oriented Object Navigation With Graph-Based Exploration CVPR 2021 Specializing Versatile Skill Libraries using Local Mixture of Experts CoRL 2021 Spectral Normalisation for Deep Reinforcement Learning: An Optimisation Perspective ICML 2021 Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation NeurIPS 2021 Stabilizing Q Learning Via Soft Mellowmax Operator AAAI 2021 Stable-Baselines3: Reliable Reinforcement Learning Implementations JMLR 2021