Towards Socially Intelligent Agents with Mental State Transition and Human Utility
arXiv:2103.07011
Abstract
Building a socially intelligent agent involves many challenges. One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human. Towards this end, we propose to incorporate mental state simulation and value modeling into dialogue agents. First, we build a hybrid mental state parser that extracts information from both the dialogue and event observations and maintains a graphical representation of the agent's mind; Meanwhile, the transformer-based value model learns human preferences from the human value dataset, ValueNet. Empirical results show that the proposed model attains state-of-the-art performance on the dialogue/action/emotion prediction task in the fantasy text-adventure game dataset, LIGHT. We also show example cases to demonstrate: (i) how the proposed mental state parser can assist the agent's decision by grounding on the context like locations and objects, and (ii) how the value model can help the agent make decisions based on its personal priorities.
arXiv commentLong paper accepted by SIGDIAL 2022
References in corpus (13)
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Deep Learning using Rectified Linear Units (ReLU)
- Bidirectional Attention Flow for Machine Comprehension
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- TextWorld: A Learning Environment for Text-based Games
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Counting to Explore and Generalize in Text-based Games
- Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
- A Paradigm for Situated and Goal-Driven Language Learning