Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)
-
Updated
Apr 16, 2018 - Python
Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)
Implementation of the Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning by Tianmin Shu, Caiming Xiong, and Richard Socher
Training anki robots to do simple things e.g. "go to the green cup"
Implementation of EMNLP 2017 Paper "Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog" using PyTorch and ParlAI
A Pytorch implemention for some state-of-the-art models for" Temporally Language Grounding in Untrimmed Videos"
Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video (AAAI2020)
A package that uses BabyAI in a sender/receiver setup.
[ICLR 2022 Spotlight] Multi-Stage Episodic Control for Strategic Exploration in Text Games
This repo contains the implelemtation for a simple language grounding in python using the robot Pepper and dockers running the servers for language groundind and speech recognition.
NeurIPS 2022 Paper "VLMbench: A Compositional Benchmark for Vision-and-Language Manipulation"
Official code for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"
Large-scale pretrained models for goal-directed dialog
This framework provides out-of-the-box implementations of Referential Games variants in order to study the emergence of artificial languages using deep learning, relying on PyTorch (https://www.pytorch.org).
[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Open Platform for Embodied Agents.
Add a description, image, and links to the language-grounding topic page so that developers can more easily learn about it.
To associate your repository with the language-grounding topic, visit your repo's landing page and select "manage topics."