{"total":18,"rows":[{"id":"2305.13660","title":"Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning","created":"2023-05-23","cited_by_count":61,"area":null},{"id":"2305.04147","title":"Controllable Mixed-Initiative Dialogue Generation through Prompting","created":"2023-05-06","cited_by_count":32,"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":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"area":null},{"id":"2108.13679","title":"Task-Oriented Dialogue System as Natural Language Generation","created":"2021-08-31","cited_by_count":14,"area":null},{"id":"2207.11762","title":"Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System","created":"2022-07-24","cited_by_count":8,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2111.01398","title":"Integrating Pretrained Language Model for Dialogue Policy Learning","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2205.10363","title":"Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2108.13811","title":"TREND: Trigger-Enhanced Relation-Extraction Network for Dialogues","created":"2021-08-31","cited_by_count":3,"area":null},{"id":"2204.11481","title":"\"Think Before You Speak\": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs","created":"2022-04-25","cited_by_count":3,"area":null},{"id":"2202.11098","title":"Hybrid Learning for Orchestrating Deep Learning Inference in Multi-user Edge-cloud Networks","created":"2022-02-21","cited_by_count":2,"area":null},{"id":"2111.01414","title":"A Review of Dialogue Systems: From Trained Monkeys to Stochastic Parrots","created":"2021-11-02","cited_by_count":1,"area":null},{"id":"2303.08470","title":"Who's in Charge? Roles and Responsibilities of Decision-Making Components in Conversational Robots","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2303.13465","title":"Deep RL with Hierarchical Action Exploration for Dialogue Generation","created":"2023-03-22","cited_by_count":1,"area":null},{"id":"2305.17433","title":"A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System","created":"2023-05-27","cited_by_count":1,"area":null},{"id":"2205.15056","title":"Stock Trading Optimization through Model-based Reinforcement Learning with Resistance Support Relative Strength","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2307.06721","title":"Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative","created":"2023-07-13","cited_by_count":0,"area":null}],"next_cursor":null}