Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning

TL;DR

This paper introduces LE2, a reinforcement learning algorithm that uses natural language interactions with a social partner to enable autonomous goal discovery, learning reward functions, and building a behavioral repertoire through curiosity-driven exploration.

Contribution

It presents a novel method for grounding language in autonomous agents, combining intrinsic motivation with natural language to facilitate self-guided goal learning.

Findings

Agent successfully grounds NL descriptions into behavioral goals

Learns a curriculum of simple to complex goals autonomously

Demonstrates effective exploration with a simulated robotic arm

Abstract

Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate their thought. We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP). Using NL descriptions from the SP, it can learn an NL-conditioned reward function to formulate goals for intrinsically motivated goal exploration and learn a goal-conditioned policy. By exploring, collecting descriptions from the SP and jointly learning the reward function and the policy, the agent grounds NL descriptions into real behavioral goals. From simple goals discovered early to more complex goals discovered by experimenting on simpler ones, our agent autonomously builds its own behavioral repertoire. This naturally occurring curriculum is supplemented by an active learning curriculum resulting from the agent's intrinsic motivations. Experiments are presented with a simulated robotic arm that interacts with several objects including tools.