A look-ahead multi-entity Transformer for modeling coordinated agents.

Last update: Dec 16, 2022

Related tags

Overview

`baller2vec++`

This is the repository for the paper:

Michael A. Alcorn and Anh Nguyen. baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents. arXiv. 2021.


To learn statistically dependent agent trajectories, `baller2vec++` uses a specially designed self-attention mask to simultaneously process three different sets of features vectors in a single Transformer. The three sets of feature vectors consist of location feature vectors like those found in `baller2vec`, look-ahead trajectory feature vectors, and starting location feature vectors. This design allows the model to integrate information about concurrent agent trajectories through multiple Transformer layers without seeing the future (in contrast to `baller2vec`).

To learn statistically dependent agent trajectories, baller2vec++ uses a specially designed self-attention mask to simultaneously process three different sets of features vectors in a single Transformer. The three sets of feature vectors consist of location feature vectors like those found in baller2vec, look-ahead trajectory feature vectors, and starting location feature vectors. This design allows the model to integrate information about concurrent agent trajectories through multiple Transformer layers without seeing the future (in contrast to baller2vec).


Training sample	`baller2vec`	`baller2vec++`

When trained on a dataset of perfectly coordinated agent trajectories, the trajectories generated by baller2vec are completely uncoordinated while the trajectories generated by baller2vec++ are perfectly coordinated.


Ground truth	`baller2vec`	`baller2vec`	`baller2vec`

Ground truth	`baller2vec++`	`baller2vec++`	`baller2vec++`

While baller2vec occasionally generates realistic trajectories for the red defender, it also makes egregious errors. In contrast, the trajectories generated by baller2vec++ often seem plausible. The red player was placed last in the player order when generating his trajectory with baller2vec++.

Citation

If you use this code for your own research, please cite:

@article{alcorn2021baller2vec,
   title={\texttt{baller2vec++}: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agents},
   author={Alcorn, Michael A. and Nguyen, Anh},
   journal={arXiv preprint arXiv:2104.11980},
   year={2021}
}

Training `baller2vec++`

Setting up `.basketball_profile`

After you've cloned the repository to your desired location, create a file called .basketball_profile in your home directory:

nano ~/.basketball_profile

and copy and paste in the contents of .basketball_profile, replacing each of the variable values with paths relevant to your environment. Next, add the following line to the end of your ~/.bashrc:

source ~/.basketball_profile

and either log out and log back in again or run:

source ~/.bashrc

You should now be able to copy and paste all of the commands in the various instructions sections. For example:

echo ${PROJECT_DIR}

should print the path you set for PROJECT_DIR in .basketball_profile.

Installing the necessary Python packages

cd ${PROJECT_DIR}
pip3 install --upgrade -r requirements.txt

Organizing the play-by-play and tracking data

Copy events.zip (which I acquired from here [mirror here] using https://downgit.github.io) to the DATA_DIR directory and unzip it:

mkdir -p ${DATA_DIR}
cp ${PROJECT_DIR}/events.zip ${DATA_DIR}
cd ${DATA_DIR}
unzip -q events.zip
rm events.zip

Descriptions for the various EVENTMSGTYPEs can be found here (mirror here).

Clone the tracking data from here (mirror here) to the DATA_DIR directory:

cd ${DATA_DIR}
git clone [email protected]:linouk23/NBA-Player-Movements.git

A description of the tracking data can be found here.

Generating the training data

cd ${PROJECT_DIR}
nohup python3 generate_game_numpy_arrays.py > data.log &

You can monitor its progress with:

top

or:

ls -U ${GAMES_DIR} | wc -l

There should be 1,262 NumPy arrays (corresponding to 631 X/y pairs) when finished.

Running the training script

Run (or copy and paste) the following script, editing the variables as appropriate.

#!/usr/bin/env bash

JOB=$(date +%Y%m%d%H%M%S)

echo "train:" >> ${JOB}.yaml
task=basketball  # "basketball" or "toy".
echo "  task: ${task}" >> ${JOB}.yaml
if [[ "$task" = "basketball" ]]
then

    echo "  train_valid_prop: 0.95" >> ${JOB}.yaml
    echo "  train_prop: 0.95" >> ${JOB}.yaml
    echo "  train_samples_per_epoch: 20000" >> ${JOB}.yaml
    echo "  valid_samples: 1000" >> ${JOB}.yaml
    echo "  workers: 10" >> ${JOB}.yaml
    echo "  learning_rate: 1.0e-5" >> ${JOB}.yaml
    echo "  patience: 20" >> ${JOB}.yaml

    echo "dataset:" >> ${JOB}.yaml
    echo "  hz: 5" >> ${JOB}.yaml
    echo "  secs: 4.2" >> ${JOB}.yaml
    echo "  player_traj_n: 11" >> ${JOB}.yaml
    echo "  max_player_move: 4.5" >> ${JOB}.yaml

    echo "model:" >> ${JOB}.yaml
    echo "  embedding_dim: 20" >> ${JOB}.yaml
    echo "  sigmoid: none" >> ${JOB}.yaml
    echo "  mlp_layers: [128, 256, 512]" >> ${JOB}.yaml
    echo "  nhead: 8" >> ${JOB}.yaml
    echo "  dim_feedforward: 2048" >> ${JOB}.yaml
    echo "  num_layers: 6" >> ${JOB}.yaml
    echo "  dropout: 0.0" >> ${JOB}.yaml
    echo "  b2v: False" >> ${JOB}.yaml

else

    echo "  workers: 10" >> ${JOB}.yaml
    echo "  learning_rate: 1.0e-4" >> ${JOB}.yaml

    echo "model:" >> ${JOB}.yaml
    echo "  embedding_dim: 20" >> ${JOB}.yaml
    echo "  sigmoid: none" >> ${JOB}.yaml
    echo "  mlp_layers: [64, 128]" >> ${JOB}.yaml
    echo "  nhead: 4" >> ${JOB}.yaml
    echo "  dim_feedforward: 512" >> ${JOB}.yaml
    echo "  num_layers: 2" >> ${JOB}.yaml
    echo "  dropout: 0.0" >> ${JOB}.yaml
    echo "  b2v: True" >> ${JOB}.yaml

fi

# Save experiment settings.
mkdir -p ${EXPERIMENTS_DIR}/${JOB}
mv ${JOB}.yaml ${EXPERIMENTS_DIR}/${JOB}/

gpu=0
cd ${PROJECT_DIR}
nohup python3 train_baller2vecplusplus.py ${JOB} ${gpu} > ${EXPERIMENTS_DIR}/${JOB}/train.log &

A look-ahead multi-entity Transformer for modeling coordinated agents.

Related tags

Overview

`baller2vec++`

Citation

Training `baller2vec++`

Setting up `.basketball_profile`

Installing the necessary Python packages

Organizing the play-by-play and tracking data

Generating the training data

Running the training script

Owner

Michael A. Alcorn

ThinkTwice: A Two-Stage Method for Long-Text Machine Reading Comprehension

Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.

Code for the paper "Are Sixteen Heads Really Better than One?"

DeLighT: Very Deep and Light-Weight Transformers

A Python script which randomly chooses and prints a file from a directory.

Implementation of TTS with combination of Tacotron2 and HiFi-GAN

Athena is an open-source implementation of end-to-end speech processing engine.

GNES enables large-scale index and semantic search for text-to-text, image-to-image, video-to-video and any-to-any content form

HuggingTweets - Train a model to generate tweets

Open source annotation tool for machine learning practitioners.

Study German declensions (dER nettE Mann, ein nettER Mann, mit dEM nettEN Mann, ohne dEN nettEN Mann ...) Generate as many exercises as you want using the incredible power of SPACY!

KR-FinBert And KR-FinBert-SC

Spam filtering made easy for you

NLPretext packages in a unique library all the text preprocessing functions you need to ease your NLP project.

End-to-end MLOps pipeline of a BERT model for emotion classification.

Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Toy example of an applied ML pipeline for me to experiment with MLOps tools.

Tools to download and cleanup Common Crawl data

🌐 Translation microservice powered by AI

PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis

A look-ahead multi-entity Transformer for modeling coordinated agents.

Related tags

Overview

baller2vec++

Citation

Training baller2vec++

Setting up .basketball_profile

Installing the necessary Python packages

Organizing the play-by-play and tracking data

Generating the training data

Running the training script

Owner

Michael A. Alcorn

ThinkTwice: A Two-Stage Method for Long-Text Machine Reading Comprehension

Cherche (search in French) allows you to create a neural search pipeline using retrievers and pre-trained language models as rankers.

Code for the paper "Are Sixteen Heads Really Better than One?"

DeLighT: Very Deep and Light-Weight Transformers

A Python script which randomly chooses and prints a file from a directory.

Implementation of TTS with combination of Tacotron2 and HiFi-GAN

Athena is an open-source implementation of end-to-end speech processing engine.

GNES enables large-scale index and semantic search for text-to-text, image-to-image, video-to-video and any-to-any content form

HuggingTweets - Train a model to generate tweets

Open source annotation tool for machine learning practitioners.

Study German declensions (dER nettE Mann, ein nettER Mann, mit dEM nettEN Mann, ohne dEN nettEN Mann ...) Generate as many exercises as you want using the incredible power of SPACY!

KR-FinBert And KR-FinBert-SC

Spam filtering made easy for you

NLPretext packages in a unique library all the text preprocessing functions you need to ease your NLP project.

End-to-end MLOps pipeline of a BERT model for emotion classification.

Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".

Toy example of an applied ML pipeline for me to experiment with MLOps tools.

Tools to download and cleanup Common Crawl data

🌐 Translation microservice powered by AI

PyABSA - Open & Efficient for Framework for Aspect-based Sentiment Analysis

`baller2vec++`

Training `baller2vec++`

Setting up `.basketball_profile`