GLIDE-RL: Grounded Language Instruction through DEmonstration in RL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kharyal, Chaitanya, Gottipati, Sai Krishna, Sinha, Tanmay Kumar, Das, Srijita, Taylor, Matthew E.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913187654270976
author Kharyal, Chaitanya
Gottipati, Sai Krishna
Sinha, Tanmay Kumar
Das, Srijita
Taylor, Matthew E.
author_facet Kharyal, Chaitanya
Gottipati, Sai Krishna
Sinha, Tanmay Kumar
Das, Srijita
Taylor, Matthew E.
contents One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors. Several advances in reinforcement learning, curriculum learning, continual learning, language models have independently contributed to effective training of grounded agents in various environments. Leveraging these developments, we present a novel algorithm, Grounded Language Instruction through DEmonstration in RL (GLIDE-RL) that introduces a teacher-instructor-student curriculum learning framework for training an RL agent capable of following natural language instructions that can generalize to previously unseen language instructions. In this multi-agent framework, the teacher and the student agents learn simultaneously based on the student's current skill level. We further demonstrate the necessity for training the student agent with not just one, but multiple teacher agents. Experiments on a complex sparse reward environment validates the effectiveness of our proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02991
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
Kharyal, Chaitanya
Gottipati, Sai Krishna
Sinha, Tanmay Kumar
Das, Srijita
Taylor, Matthew E.
Computation and Language
Artificial Intelligence
Machine Learning
One of the final frontiers in the development of complex human - AI collaborative systems is the ability of AI agents to comprehend the natural language and perform tasks accordingly. However, training efficient Reinforcement Learning (RL) agents grounded in natural language has been a long-standing challenge due to the complexity and ambiguity of the language and sparsity of the rewards, among other factors. Several advances in reinforcement learning, curriculum learning, continual learning, language models have independently contributed to effective training of grounded agents in various environments. Leveraging these developments, we present a novel algorithm, Grounded Language Instruction through DEmonstration in RL (GLIDE-RL) that introduces a teacher-instructor-student curriculum learning framework for training an RL agent capable of following natural language instructions that can generalize to previously unseen language instructions. In this multi-agent framework, the teacher and the student agents learn simultaneously based on the student's current skill level. We further demonstrate the necessity for training the student agent with not just one, but multiple teacher agents. Experiments on a complex sparse reward environment validates the effectiveness of our proposed approach.
title GLIDE-RL: Grounded Language Instruction through DEmonstration in RL
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2401.02991