نسعى إلى إنشاء وكلاء يتصرفون والتواصل مع الوكلاء الآخرين في السعي لتحقيق هدف.تحقيقا لهذه الغاية، نقوم بتمديد الضوء (Urbanek et al. 2019) --- لعبة نصية خيال من الحشد على نطاق واسع - مع مجموعة بيانات من المهام.هذه تحتوي على دوافع لغوية طبيعية مقترنة بأهداف في اللعبة والمظاهرات البشرية؛قد يتطلب إكمال السعي حوار أو إجراءات (أو كليهما).نقدم نظام لتعليم التعزيز (1) يشتمل على التدريب المستندة إلى النمذجة على النمذجة القائمة على النمذجة على النمذجة على نطاق واسع ومقرها مسبقا لإشراف الوكيل مع البثور ذات الصلة؛و (2) يرفع مساحة عمل عوامل من أوامر العمل والحوار، موازنة بين الاثنين.نقوم بإجراء تقييمات طلقة صفرية باستخدام مظاهرات الخبراء البشرية المحتفظ بها، والتي تبين أن عملائنا قادرون على التصرف باستمرار والتحدث بشكل طبيعي فيما يتعلق بدوافعهم.
We seek to create agents that both act and communicate with other agents in pursuit of a goal. Towards this end, we extend LIGHT (Urbanek et al. 2019)---a large-scale crowd-sourced fantasy text-game---with a dataset of quests. These contain natural language motivations paired with in-game goals and human demonstrations; completing a quest might require dialogue or actions (or both). We introduce a reinforcement learning system that (1) incorporates large-scale language modeling-based and commonsense reasoning-based pre-training to imbue the agent with relevant priors; and (2) leverages a factorized action space of action commands and dialogue, balancing between the two. We conduct zero-shot evaluations using held-out human expert demonstrations, showing that our agents are able to act consistently and talk naturally with respect to their motivations.
References used
https://aclanthology.org/
Text-based games simulate worlds and interact with players using natural language. Recent work has used them as a testbed for autonomous language-understanding agents, with the motivation being that understanding the meanings of words or semantics is
Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pretrained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating fine-tuned
In goal-oriented dialogue systems, users provide information through slot values to achieve specific goals. Practically, some combinations of slot values can be invalid according to external knowledge. For example, a combination of cheese pizza'' (a
To be good conversational partners, natural language processing (NLP) systems should be trained to produce contextually useful utterances. Prior work has investigated training NLP systems with communication-based objectives, where a neural listener s
Myelomeningoceles are very common anamoly in our country. Mostly it ends
with permanent damage and handicap. Lot of these children die due to meningitis as a complication.
It still till now a large number of children with myelo meningoceles seek me