Dead End

"Dead ends," in various contexts, represent states in a system where progress is blocked, hindering the achievement of desired outcomes. Current research focuses on detecting and mitigating these dead ends, employing techniques like reinforcement learning with decoupled policies for safety and task performance, and adversarial attacks to assess the robustness of models relying on auxiliary information such as morphological tags. These efforts aim to improve efficiency in areas like reinforcement learning, natural language processing, and dialogue systems, ultimately leading to more robust and effective algorithms and applications.

Papers

June 24, 2023

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery
Xiao Zhang, Hai Zhang, Hongtu Zhou, Chang Huang, Di Zhang, Chen Ye, Junqiao Zhao
Reinforcement Learning Safe Reinforcement Learning Prompt Recovery Safe Exploration Continuous Control Task Safety Critic Dead End

May 24, 2023

Another Dead End for Morphological Tags? Perturbed Inputs and Parsing
Alberto Muñoz-Ortiz, David Vilares
Sequence Labeling Rich Input Morphological Tagging Neural Parser Dead End

May 5, 2023

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization
Yangyang Zhao, Zhenyu Wang, Mehdi Dastani, Shihan Wang
Deep Reinforcement Learning Efficient Exploration Dialogue Policy Dialogue Data Augmentation Dead End

January 10, 2023

Language Models sounds the Death Knell of Knowledge Graphs
Kunal Suri, Atul Singh, Prakhar Mishra, Swapna Sourav Rout, Rajesh Sabapathy
Language Model Knowledge Graph Medical Domain Unified Medical Language System Dead End

Dead End

Papers

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

Another Dead End for Morphological Tags? Perturbed Inputs and Parsing

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization

Language Models sounds the Death Knell of Knowledge Graphs