Reinforcement Learning

Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs AAAI 2021 Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare IJCAI 2021 LEOC: A Principled Method in Integrating Reinforcement Learning and Classical Control Theory L4DC 2021 Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021 Leveraging on Deep Reinforcement Learning for Autonomous Safe Decision-Making in Highway On-ramp Merging (Student Abstract) AAAI 2021 LILA: Language-Informed Latent Actions CoRL 2021 LOA: Logical Optimal Actions for Text-based Interaction Games ACL 2021 Locally Persistent Exploration in Continuous Control Tasks with Sparse Rewards ICML 2021 Local policy search with Bayesian optimization NeurIPS 2021 Logarithmic Regret for Reinforcement Learning with Linear Function Approximation ICML 2021 Logical Team Q-learning: An approach towards factored policies in cooperative MARL AISTATS 2021 Logistic Q-Learning AISTATS 2021 Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention CoRL 2021 Loop Estimator for Discounted Values in Markov Reward Processes AAAI 2021 Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision ICML 2021 LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks CoRL 2021 LTL-Constrained Steady-State Policy Synthesis IJCAI 2021 Lyapunov-stable neural-network control RSS 2021 Machine versus Human Attention in Deep Reinforcement Learning Tasks NeurIPS 2021 MADE: Exploration via Maximizing Deviation from Explored Regions NeurIPS 2021 MAGIC: Learning Macro-Actions for Online POMDP Planning RSS 2021 Manipulator-Independent Representations for Visual Imitation RSS 2021 MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks IJCAI 2021 Mapping Language to Programs using Multiple Reward Components with Inverse Reinforcement Learning EMNLP 2021 MAP Propagation Algorithm: Faster Learning with a Team of Reinforcement Learning Agents NeurIPS 2021