Methods

Discovering a set of policies for the worst case reward ICLR 2021 Discovering symbolic policies with deep reinforcement learning ICML 2021 Discovery of Options via Meta-Learned Subgoals NeurIPS 2021 Discrete-Continuous Action Space Policy Gradient-Based Attention for Image-Text Matching CVPR 2021 Distributionally Robust Imitation Learning NeurIPS 2021 Distributional Reinforcement Learning via Moment Matching AAAI 2021 Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration ICML 2021 Don’t Do What Doesn’t Matter: Intrinsic Motivation with Action Usefulness IJCAI 2021 DOP: Off-Policy Multi-Agent Decomposed Policy Gradients ICLR 2021 Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality ICML 2021 DRIVE: Deep Reinforced Accident Anticipation With Visual Explanation ICCV 2021 Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates NeurIPS 2021 Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search AAAI 2021 Dynamic Balancing for Model Selection in Bandits and RL ICML 2021 Dynamic Bottleneck for Robust Self-Supervised Exploration NeurIPS 2021 Dynamic Lane Traffic Signal Control with Group Attention and Multi-Timescale Reinforcement Learning IJCAI 2021 Dynamic population-based meta-learning for multi-agent communication with natural language NeurIPS 2021 EasyRL: A Simple and Extensible Reinforcement Learning Framework AAAI 2021 ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning EACL 2021 Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy EMNLP 2021 Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement EMNLP 2021 Efficient PAC Reinforcement Learning in Regular Decision Processes IJCAI 2021 Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations ICML 2021 Efficient Reinforcement Learning in Factored MDPs with Application to Constrained RL ICLR 2021 EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL ICML 2021