Policy Learning

SCAPE: Learning Stiffness Control from Augmented Position Control Experiences CoRL 2021 Self-Consistent Models and Values NeurIPS 2021 Settling the Variance of Multi-Agent Policy Gradients NeurIPS 2021 Skill Discovery for Exploration and Planning using Deep Skill Graphs ICML 2021 Softmax Policy Gradient Methods Can Take Exponential Time to Converge COLT 2021 Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract) AAAI 2021 Specializing Versatile Skill Libraries using Local Mixture of Experts CoRL 2021 Stabilizing Dynamical Systems via Policy Gradient Methods NeurIPS 2021 State-Wise Adaptive Discounting from Experience (SADE): A Novel Discounting Scheme for Reinforcement Learning (Student Abstract) AAAI 2021 Synthesis of Search Heuristics for Temporal Planning via Reinforcement Learning AAAI 2021 Tactical Optimism and Pessimism for Deep Reinforcement Learning NeurIPS 2021 Taylor Expansion of Discount Factors ICML 2021 Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks AAAI 2021 TempoRL: Learning When to Act ICML 2021 The benefits of sharing: a cloud-aided performance-driven framework to learn optimal feedback policies L4DC 2021 The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition NeurIPS 2021 The Emergence of Individuality ICML 2021 The Logical Options Framework ICML 2021 The Sample Complexity of Teaching by Reinforcement on Q-Learning AAAI 2021 The Successful Ingredients of Policy Gradient Algorithms IJCAI 2021 ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning CoRL 2021 Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods NeurIPS 2021 Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning NeurIPS 2021 Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning ICML 2021 Towards Tight Bounds on the Sample Complexity of Average-reward MDPs ICML 2021