GLIDE-RL: Grounded Language Instruction through DEmonstration in RL | AAMAS 2024

This work was presented at the The 23rd International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS) 2024. The preprint was released on arXiv on Jan the 9th 2024.

Abstract

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.

You can learn more about this work in a dedicated blog post

Cite

@inproceedings{gliderl2024,
      title={GLIDE-RL: Grounded Language Instruction through DEmonstration in RL}, 
      author={
        Chaitanya Kharyal and 
        Sai Krishna Gottipati and 
        Tanmay Kumar Sinha and 
        Srijita Das and 
        Matthew E. Taylor
      },
      booktitle={Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems},
      year={2024}
}