Methods

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation ICLR 2022 Corruption-robust Offline Reinforcement Learning AISTATS 2022 Creating Interactive Crowds with Reinforcement Learning AAAI 2022 Creativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning AAAI 2022 Criticality-Based Advice in Reinforcement Learning (Student Abstract) AAAI 2022 CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing ICLR 2022 Cross-domain adaptive transfer reinforcement learning based on state-action correspondence UAI 2022 Cross-Domain Imitation Learning via Optimal Transport ICLR 2022 CrowdPlay: Crowdsourcing Human Demonstrations for Offline Learning ICLR 2022 CtrlFormer: Learning Transferable State Representation for Visual Control via Transformer ICML 2022 CUP: Critic-Guided Policy Reuse NeurIPS 2022 Curiosity-Driven Exploration via Latent Bayesian Surprise AAAI 2022 Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation NeurIPS 2022 Curriculum Reinforcement Learning via Constrained Optimal Transport ICML 2022 d3rlpy: An Offline Deep Reinforcement Learning Library JMLR 2022 DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning ICLR 2022 DASCO: Dual-Generator Adversarial Support Constrained Offline Reinforcement Learning NeurIPS 2022 Data augmentation for efficient learning from parametric experts NeurIPS 2022 Data-Driven Offline Decision-Making via Invariant Representation Learning NeurIPS 2022 Data-Efficient Model Learning for Control with Jacobian-Regularized Dynamic-Mode Decomposition CoRL 2022 Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data NeurIPS 2022 DayDreamer: World Models for Physical Robot Learning CoRL 2022 Dealing with Non-Stationarity in MARL via Trust-Region Decomposition ICLR 2022 Decentralized Cooperative Reinforcement Learning with Hierarchical Information Structure ALT 2022 Decentralized Mean Field Games AAAI 2022