Policy Learning

Distributionally Robust Imitation Learning NeurIPS 2021 Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration ICML 2021 Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates NeurIPS 2021 Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy EMNLP 2021 Efficient PAC Reinforcement Learning in Regular Decision Processes IJCAI 2021 Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations ICML 2021 Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser EMNLP 2021 Escaping from zero gradient: Revisiting action-constrained reinforcement learning via Frank-Wolfe policy optimization UAI 2021 Exact Asymptotics for Linear Quadratic Adaptive Control JMLR 2021 Expected Eligibility Traces AAAI 2021 Explaining fast improvement in online imitation learning UAI 2021 Explicable Reward Design for Reinforcement Learning Agents NeurIPS 2021 Exploration by Maximizing Renyi Entropy for Reward-Free RL Framework AAAI 2021 Exploring Dynamic Selection of Branch Expansion Orders for Code Generation ACL 2021 Extending Policy Shaping to Continuous State Spaces (Student Abstract) AAAI 2021 Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs NeurIPS 2021 Faster Policy Learning with Continuous-Time Gradients L4DC 2021 Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021 Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm ICML 2021 First-Order Methods for Wasserstein Distributionally Robust MDP ICML 2021 Generalizable Imitation Learning from Observation via Inferring Goal Proximity NeurIPS 2021 Generalization in Text-based Games via Hierarchical Reinforcement Learning EMNLP 2021 Generalized Proximal Policy Optimization with Sample Reuse NeurIPS 2021 Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning EMNLP 2021 Global Convergence of Policy Gradient for Linear-Quadratic Mean-Field Control/Game in Continuous Time ICML 2021