Neural Reasoning about Agents' Goals, Preferences, and Actions

**[Matteo Bortoletto][1],   [Lei Shi][2],   [Andreas Bulling][3]**

**AAAI'24, Vancouver, CA**
# Citation If you find our code useful or use it in your own projects, please cite our paper: ```bibtex @inproceedings{bortoletto2024neural, title={Neural Reasoning About Agents’ Goals, Preferences, and Actions}, author={Bortoletto, Matteo and Shi, Lei and Bulling, Andreas}, booktitle={Proceedings of the AAAI Conference on Artificial Intelligence}, volume={38}, number={1}, pages={456--464}, year={2024} } ``` # Setup This code is based on the [original implementation][5] of the BIB benchmark. ## Using `virtualenv` ```bash python -m virtualenv /path/to/env source /path/to/env/bin/activate pip install -r requirements.txt ``` ## Using `conda` ```bash conda create --name python=3.8.10 pip=20.0.2 cudatoolkit=10.2.89 conda activate pip install -r requirements_conda.txt pip install dgl-cu102 dglgo -f ``` # Running the code ## Activate the environment Run `source bibdgl/bin/activate`. ## Index data This will create the json files with all the indexed frames for each episode in each video. ```bash python utils/ ``` You need to manually set `mode` in the dataset class (in main). ## Generate graphs This will generate the graphs from the videos: ```bash python /utils/ --mode MODE --cpus NUM_CPUS ``` `MODE` can be `train`, `val` or `test`. NOTE: check `utils/` to make sure you're loading the correct dataset to generate the graphs you want. ## Training Use `CUDA_VISIBLE_DEVICES=0`. ## Testing Use `CUDA_VISIBLE_DEVICES=0`. # Hardware setup All models are trained on an NVIDIA Tesla V100-SXM2-32GB GPU. [1]: [2]: [3]: [4]: [5]: