Automatic Exploration of Textual Environments with Language-Conditioned Autotelic Agents
This work proposes a framework for advancing autonomous agents in text-based environments, which could benefit AI research in natural language understanding and interactive systems, though it appears incremental as it builds on existing concepts.
The paper discusses the potential of using intrinsically-motivated agents for exploration in textual environments, identifying key properties of text worlds that facilitate such exploration and outlining specific challenges that need to be addressed.
In this extended abstract we discuss the opportunities and challenges of studying intrinsically-motivated agents for exploration in textual environments. We argue that there is important synergy between text environments and autonomous agents. We identify key properties of text worlds that make them suitable for exploration by autonmous agents, namely, depth, breadth, progress niches and the ease of use of language goals; we identify drivers of exploration for such agents that are implementable in text worlds. We discuss the opportunities of using autonomous agents to make progress on text environment benchmarks. Finally we list some specific challenges that need to be overcome in this area.