Towards Teachable Autotelic Agents

TL;DR

This paper proposes a roadmap for developing teachable autotelic agents that combine autonomous learning with guided instruction, inspired by developmental psychology, to improve AI learning efficiency and human interaction.

Contribution

It introduces a checklist of features for teachable autotelic agents, bridging developmental psychology and AI to guide future research and design.

Findings

Identified key features for assisted discovery in child-tutor interactions

Pinpointed limitations of current reinforcement learning agents

Outlined research directions for human-taught autonomous agents

Abstract

Autonomous discovery and direct instruction are two distinct sources of learning in children but education sciences demonstrate that mixed approaches such as assisted discovery or guided play result in improved skill acquisition. In the field of Artificial Intelligence, these extremes respectively map to autonomous agents learning from their own signals and interactive learning agents fully taught by their teachers. In between should stand teachable autotelic agents (TAA): agents that learn from both internal and teaching signals to benefit from the higher efficiency of assisted discovery. Designing such agents will enable real-world non-expert users to orient the learning trajectories of agents towards their expectations. More fundamentally, this may also be a key step to build agents with human-level intelligence. This paper presents a roadmap towards the design of teachable autonomous agents. Building on developmental psychology and education sciences, we start by identifying key features enabling assisted discovery processes in child-tutor interactions. This leads to the production of a checklist of features that future TAA will need to demonstrate. The checklist allows us to precisely pinpoint the various limitations of current reinforcement learning agents and to identify the promising first steps towards TAA. It also shows the way forward by highlighting key research directions towards the design or autonomous agents that can be taught by ordinary people via natural pedagogy.