The adoption of pre-trained language models to generate action plans for embodied agents is a promising research strategy. However, execution of instructions in real or simulated environments requires verification of the feasibility of actions as well as their relevance to the completion of a goal. We propose a new method that combines a language model and reinforcement learning for the task of building objects in a Minecraft-like environment according to the natural language instructions. Our method first generates a set of consistently achievable sub-goals from the instructions and then completes associated sub-tasks with a pre-trained RL policy. The proposed method formed the RL baseline at the IGLU 2022 competition.
@article{arxiv.2211.00688,
title = {Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions},
author = {Alexey Skrynnik and Zoya Volovikova and Marc-Alexandre Côté and Anton Voronov and Artem Zholus and Negar Arabzadeh and Shrestha Mohanty and Milagro Teruel and Ahmed Awadallah and Aleksandr Panov and Mikhail Burtsev and Julia Kiseleva},
journal= {arXiv preprint arXiv:2211.00688},
year = {2022}
}