DeepAI AI Chat
Log In Sign Up

Situated Dialogue Learning through Procedural Environment Generation

by   Prithviraj Ammanabrolu, et al.
Allen Institute for Artificial Intelligence

We teach goal-driven agents to interactively act and speak in situated environments by training on generated curriculums. Our agents operate in LIGHT (Urbanek et al. 2019) – a large-scale crowd-sourced fantasy text adventure game wherein an agent perceives and interacts with the world through textual natural language. Goals in this environment take the form of character-based quests, consisting of personas and motivations. We augment LIGHT by learning to procedurally generate additional novel textual worlds and quests to create a curriculum of steadily increasing difficulty for training agents to achieve such goals. In particular, we measure curriculum difficulty in terms of the rarity of the quest in the original training distribution – an easier environment is one that is more likely to have been found in the unaugmented dataset. An ablation study shows that this method of learning from the tail of a distribution results in significantly higher generalization abilities as measured by zero-shot performance on never-before-seen quests.


page 1

page 14


How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds

We seek to create agents that both act and communicate with other agents...

It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation

We are interested in training general-purpose reinforcement learning age...

Learning Knowledge Graph-based World Models of Textual Environments

World models improve a learning agent's ability to efficiently operate i...

Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration

Autonomous reinforcement learning agents must be intrinsically motivated...

A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld

Building open-ended agents that can autonomously discover a diversity of...

PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation

Curriculum Data Augmentation (CDA) improves neural models by presenting ...

Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents

In this extended abstract we discuss the opportunities and challenges of...