{"total":23,"rows":[{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39,"area":null},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30,"area":null},{"id":"2106.03039","title":"Multi-facet Contextual Bandits: A Neural Network Perspective","created":"2021-06-06","cited_by_count":20,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2204.05928","title":"Dynamic Dialogue Policy for Continual Reinforcement Learning","created":"2022-04-12","cited_by_count":12,"area":null},{"id":"2201.06849","title":"Toward Self-learning End-to-End Task-Oriented Dialog Systems","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2201.13395","title":"Neural Collaborative Filtering Bandits via Meta Learning","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2408.05586","title":"Meta Clustering of Neural Bandits","created":"2024-08-10","cited_by_count":7,"area":null},{"id":"2212.06564","title":"Prescriptive Process Monitoring in Intelligent Process Automation with Chatbot Orchestration","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2312.04668","title":"TOD-Flow: Modeling the Structure of Task-Oriented Dialogues","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2106.00891","title":"High-Quality Diversification for Task-Oriented Dialogue Systems","created":"2021-06-02","cited_by_count":3,"area":null},{"id":"2109.07129","title":"What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2308.13049","title":"Bayesian Exploration Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2106.11086","title":"Analytically Tractable Bayesian Deep Q-Learning","created":"2021-06-21","cited_by_count":2,"area":null},{"id":"2210.15670","title":"Knowledge-Guided Exploration in Deep Reinforcement Learning","created":"2022-10-26","cited_by_count":2,"area":null},{"id":"2302.04250","title":"Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2305.03262","title":"Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2308.01210","title":"Global Hierarchical Neural Networks using Hierarchical Softmax","created":"2023-08-02","cited_by_count":1,"area":null},{"id":"2204.09719","title":"Recent Progress in Conversational AI","created":"2022-04-08","cited_by_count":0,"area":null},{"id":"2207.00468","title":"Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings","created":"2022-07-01","cited_by_count":0,"area":null}],"next_cursor":null}