Reinforced Natural Language Interfaces via Entropy Decomposition
arXiv:2109.11408
Abstract
In this paper, we study the technical problem of developing conversational agents that can quickly adapt to unseen tasks, learn task-specific communication tactics, and help listeners finish complex, temporally extended tasks. We find that the uncertainty of language learning can be decomposed to an entropy term and a mutual information term, corresponding to the structural and functional aspect of language, respectively. Combined with reinforcement learning, our method automatically requests human samples for training when adapting to new tasks and learns communication protocols that are succinct and helpful for task completion. Human and simulation test results on a referential game and a 3D navigation game prove the effectiveness of the proposed method.
References in corpus (11)
- Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
- A Simple Language Model for Task-Oriented Dialogue
- SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
- An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
- Anti-efficient encoding in emergent communication
- Generative Deep Neural Networks for Dialogue: A Short Review
- Multi-lingual Intent Detection and Slot Filling in a Joint BERT-based Model
- InfoBot: Transfer and Exploration via the Information Bottleneck
- Emergent Multi-Agent Communication in the Deep Learning Era
- Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models
- Transferable Dialogue Systems and User Simulators