Reinforcement Learning

Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations ACL 2021 ELLA: Exploration through Learned Language Abstraction NeurIPS 2021 EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL ICML 2021 Embodied Semantic Scene Graph Generation CoRL 2021 Embodied Visual Active Learning for Semantic Segmentation AAAI 2021 Emergent Discrete Communication in Semantic Spaces NeurIPS 2021 Emergent Prosociality in Multi-Agent Games Through Gifting IJCAI 2021 Emergent Road Rules In Multi-Agent Driving Environments ICLR 2021 Emergent Social Learning via Multi-agent Reinforcement Learning ICML 2021 Emphatic Algorithms for Deep Reinforcement Learning ICML 2021 Encoding Human Domain Knowledge to Warm Start Reinforcement Learning AAAI 2021 End-to-End Egospheric Spatial Memory ICLR 2021 End-to-End Urban Driving by Imitating a Reinforcement Learning Coach ICCV 2021 Enhancing Context-Based Meta-Reinforcement Learning Algorithms via An Efficient Task Encoder (Student Abstract) AAAI 2021 Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser EMNLP 2021 Ensemble Bootstrapping for Q-Learning ICML 2021 Entropic Desired Dynamics for Intrinsic Control NeurIPS 2021 Environment Generation for Zero-Shot Compositional Reinforcement Learning NeurIPS 2021 Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety L4DC 2021 Episodic Multi-agent Reinforcement Learning with Curiosity-driven Exploration NeurIPS 2021 Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited ALT 2021 ER-AE: Differentially Private Text Generation for Authorship Anonymization NAACL 2021 Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation CoRL 2021 Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments RSS 2021 Escaping from zero gradient: Revisiting action-constrained reinforcement learning via Frank-Wolfe policy optimization UAI 2021