Agent Systems

Don’t be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System EMNLP 2021 Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration ICLR 2021 Dual-Mandate Patrols: Multi-Armed Bandits for Green Security AAAI 2021 Duplex Conversation in Outbound Agent System Interspeech 2021 DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation EMNLP 2021 Dynamics-regulated kinematic policy for egocentric pose estimation NeurIPS 2021 Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory Policy EMNLP 2021 Emergent Communication of Generalizations NeurIPS 2021 Enabling Fast Instruction-Based Modification of Learned Robot Skills AAAI 2021 Encoding Human Domain Knowledge to Warm Start Reinforcement Learning AAAI 2021 Enforcing robust control guarantees within neural network policies ICLR 2021 Episodic Learning for Safe Bipedal Locomotion with Control Barrier Functions and Projection-to-State Safety L4DC 2021 Everyday Living Artificial Intelligence Hub NAACL 2021 Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions ALT 2021 Extending Lagrangian and Hamiltonian Neural Networks with Differentiable Contact Models NeurIPS 2021 Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments ICLR 2021 Factorizing Perception and Policy for Interactive Instruction Following ICCV 2021 Fast and Efficient Locomotion via Learned Gait Transitions CoRL 2021 Fast And Slow Learning Of Recurrent Independent Mechanisms ICLR 2021 FAST: Financial News and Tweet Based Time Aware Network for Stock Trading EACL 2021 Feature-Based SLAM: Why Simultaneous Localisation and Mapping? RSS 2021 Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language Understanding EMNLP 2021 Fitting summary statistics of neural data with a differentiable spiking network simulator NeurIPS 2021 Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation NeurIPS 2021 Fully Gap-Dependent Bounds for Multinomial Logit Bandit AISTATS 2021