Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)

Last update: Nov 05, 2022

Overview

Gated-Attention Architectures for Task-Oriented Language Grounding

This is a PyTorch implementation of the AAAI-18 paper:

Gated-Attention Architectures for Task-Oriented Language Grounding
Devendra Singh Chaplot, Kanthashree Mysore Sathyendra, Rama Kumar Pasumarthi, Dheeraj Rajagopal, Ruslan Salakhutdinov
Carnegie Mellon University

Project Website: https://sites.google.com/view/gated-attention

This repository contains:

Code for training an A3C-LSTM agent using Gated-Attention
Code for Doom-based language grounding environment

Dependencies

ViZDoom
PyTorch
Opencv

(We recommend using Anaconda)

Usage

Using the Environment

For running a random agent:

python env_test.py

To play in the environment:

python env_test.py --interactive 1

To change the difficulty of the environment (easy/medium/hard):

python env_test.py -d easy

Training Gated-Attention A3C-LSTM agent

For training a A3C-LSTM agent with 32 threads:

python a3c_main.py --num-processes 32 --evaluate 0

The code will save the best model at ./saved/model_best.

To the test the pre-trained model for Multitask Generalization:

python a3c_main.py --evaluate 1 --load saved/pretrained_model

To the test the pre-trained model for Zero-shot Task Generalization:

python a3c_main.py --evaluate 2 --load saved/pretrained_model

To the visualize the model while testing add '--visualize 1':

python a3c_main.py --evaluate 2 --load saved/pretrained_model --visualize 1

To test the trained model, use --load saved/model_best in the above commands.

All arguments for a3c_main.py:

  -h, --help            show this help message and exit
  -l MAX_EPISODE_LENGTH, --max-episode-length MAX_EPISODE_LENGTH
                        maximum length of an episode (default: 30)
  -d DIFFICULTY, --difficulty DIFFICULTY
                        Difficulty of the environment, "easy", "medium" or
                        "hard" (default: hard)
  --living-reward LIVING_REWARD
                        Default reward at each time step (default: 0, change
                        to -0.005 to encourage shorter paths)
  --frame-width FRAME_WIDTH
                        Frame width (default: 300)
  --frame-height FRAME_HEIGHT
                        Frame height (default: 168)
  -v VISUALIZE, --visualize VISUALIZE
                        Visualize the envrionment (default: 0, use 0 for
                        faster training)
  --sleep SLEEP         Sleep between frames for better visualization
                        (default: 0)
  --scenario-path SCENARIO_PATH
                        Doom scenario file to load (default: maps/room.wad)
  --interactive INTERACTIVE
                        Interactive mode enables human to play (default: 0)
  --all-instr-file ALL_INSTR_FILE
                        All instructions file (default:
                        data/instructions_all.json)
  --train-instr-file TRAIN_INSTR_FILE
                        Train instructions file (default:
                        data/instructions_train.json)
  --test-instr-file TEST_INSTR_FILE
                        Test instructions file (default:
                        data/instructions_test.json)
  --object-size-file OBJECT_SIZE_FILE
                        Object size file (default: data/object_sizes.txt)
  --lr LR               learning rate (default: 0.001)
  --gamma G             discount factor for rewards (default: 0.99)
  --tau T               parameter for GAE (default: 1.00)
  --seed S              random seed (default: 1)
  -n N, --num-processes N
                        how many training processes to use (default: 4)
  --num-steps NS        number of forward steps in A3C (default: 20)
  --load LOAD           model path to load, 0 to not reload (default: 0)
  -e EVALUATE, --evaluate EVALUATE
                        0:Train, 1:Evaluate MultiTask Generalization
                        2:Evaluate Zero-shot Generalization (default: 0)
  --dump-location DUMP_LOCATION
                        path to dump models and log (default: ./saved/)

Demostration videos:

Multitask Generalization video: https://www.youtube.com/watch?v=YJG8fwkv7gA

Zero-shot Task Generalization video: https://www.youtube.com/watch?v=JziCKsLrudE

Different stages of training: https://www.youtube.com/watch?v=o_G6was03N0

Cite as

Chaplot, D.S., Sathyendra, K.M., Pasumarthi, R.K., Rajagopal, D. and Salakhutdinov, R., 2017. Gated-Attention Architectures for Task-Oriented Language Grounding. arXiv preprint arXiv:1706.07230. (PDF)

Bibtex:

@article{chaplot2017gated,
  title={Gated-Attention Architectures for Task-Oriented Language Grounding},
  author={Chaplot, Devendra Singh and Sathyendra, Kanthashree Mysore and Pasumarthi, Rama Kumar and Rajagopal, Dheeraj and Salakhutdinov, Ruslan},
  journal={arXiv preprint arXiv:1706.07230},
  year={2017}
}

Acknowledgements

This repository uses ViZDoom API (https://github.com/mwydmuch/ViZDoom) and parts of the code from the API. The implementation of A3C is borrowed from https://github.com/ikostrikov/pytorch-a3c. The poisson-disc code is borrowed from https://github.com/IHautaI/poisson-disc.

Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)

Related tags

Overview

Gated-Attention Architectures for Task-Oriented Language Grounding

This repository contains:

Dependencies

Usage

Using the Environment

Training Gated-Attention A3C-LSTM agent

Demostration videos:

Cite as

Bibtex:

Acknowledgements

Owner

Devendra Chaplot

A list of awesome PyTorch scholarship articles, guides, blogs, courses and other resources.

My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)

Google Landmark Recogntion and Retrieval 2021 Solutions

Official implementation of SIGIR'2021 paper: "Sequential Recommendation with Graph Neural Networks".

Official Pytorch implementation for AAAI2021 paper (RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning)

A hobby project which includes a hand-gesture based virtual piano using a mobile phone camera and OpenCV library functions

Domain Generalization for Mammography Detection via Multi-style and Multi-view Contrastive Learning

Le dataset des images du projet d'IA de 2021

RL agent to play μRTS with Stable-Baselines3

Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.

Tensorflow/Keras Plug-N-Play Deep Learning Models Compilation

BC3407-Group-5-Project - BC3407 Group Project With Python

Text and code for the forthcoming second edition of Think Bayes, by Allen Downey.

Training BERT with Compute/Time (Academic) Budget

This repository contains several image-to-image translation models, whcih were tested for RGB to NIR image generation. The models are Pix2Pix, Pix2PixHD, CycleGAN and PointWise.

2021 CCF BDCI 全国信息检索挑战杯（CCIR-Cup）智能人机交互自然语言理解赛道第二名参赛解决方案

Approaches to modeling terrain and maps in python

Source code for Task-Aware Variational Adversarial Active Learning

QR2Pass-project - A proof of concept for an alternative (passwordless) authentication system to a web server

A platform for intelligent agent learning based on a 3D open-world FPS game developed by Inspir.AI.