Reinforcement Learning

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks ICLR 2022 Curiosity-Driven Exploration via Latent Bayesian Surprise AAAI 2022 DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning ICLR 2022 Dealing with Non-Stationarity in MARL via Trust-Region Decomposition ICLR 2022 Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning NeurIPS 2022 Deep Reinforcement Learning for High-Frequency Market Making ACML 2022 Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency AAAI 2022 DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning NeurIPS 2022 Dimensionality Reduction and Prioritized Exploration for Policy Search AISTATS 2022 Direct Advantage Estimation NeurIPS 2022 Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching ICLR 2022 Distributionally Adaptive Meta Reinforcement Learning NeurIPS 2022 DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning NeurIPS 2022 DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization ICLR 2022 Dynamics-Aware Comparison of Learned Reward Functions ICLR 2022 EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL NeurIPS 2022 Efficient Continuous Control with Double Actors and Regularized Critics AAAI 2022 Efficient Dialog Policy Learning by Reasoning with Contextual Knowledge AAAI 2022 Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization ICLR 2022 Emergent Communication at Scale ICLR 2022 EMVLight: A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehicles AAAI 2022 Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning ICLR 2022 Explainable Reinforcement Learning via Model Transforms NeurIPS 2022 Explicable Policy Search NeurIPS 2022 Exploring through Random Curiosity with General Value Functions NeurIPS 2022