ShuangLI59/Pre-Trained-Language-Models-for-Interactive-Decision-Making

Stars
115
Rank 304,148 (Top 7 %)
Language
Python
Created almost 3 years ago
Updated over 2 years ago

ShuangLI59/Pre-Trained-Language-Models-for-Interactive-Decision-Making

ShuangLI59

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Pre-Trained Language Models for Interactive Decision-Making [NeurIPS 2022]

Pre-Trained Language Models for Interactive Decision-Making

Project Page | Paper

This is the official codebase for Pre-Trained Language Models for Interactive Decision-Making.

Setup

Get the VirtualHome Simulator

Download VirtualHome exectuable file (v2.2.5). Please refer to VirtualHome for more details.

The VirtualHome exectuable file we used can be downloaded from here. Put it under ./virtualhome.

Download Checkpoints

Download the checkpoint: LID-Text. Put the checkpoint under ./behavior_cloning/checkpoint.

Inference

Download Virtualhome initial environment for testing: data. Put them under ./data.

For interactive evaluation, run:

sh scripts/inference.sh

person_search

Joint Detection and Identification Feature Learning for Person Search

Person-Search-with-Natural-Language-Description

Person Search with Natural Language Description

Diversity-Regularized-Spatiotemporal-Attention

Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification

ebm-continual-learning

Energy-Based Models for Continual Learning Official Repository (PyTorch)

weakly-supervised-human-object-detection-video

Composing-Ensembles-of-Pre-trained-Models-via-Iterative-Consensus

compositional-generalization