Code corresponding to The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

Overview

The Introspective Agent:

Interdependence of Strategy, Physiology, and Sensing for Embodied Agents

This is the code corresponding to The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents by Sarah Pratt, Luca Weihs, and Ali Farhadi.

Abstract:

The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success, biological organisms still hold one large advantage over these simulated agents: adaptation. While both living and simulated agents make decisions to achieve goals (strategy), biological organisms have evolved to understand their environment (sensing) and respond to it (physiology). The net gain of these factors depends on the environment, and organisms have adapted accordingly. For example, in a low vision aquatic environment some fish have evolved specific neurons which offer a predictable, but incredibly rapid, strategy to escape from predators. Mammals have lost these reactive systems, but they have a much larger fields of view and brain circuitry capable of understanding many future possibilities. While traditional embodied agents manipulate an environment to best achieve a goal, we argue for an introspective agent, which considers its own abilities in the context of its environment. We show that different environments yield vastly different optimal designs, and increasing long-term planning is often far less beneficial than other improvements, such as increased physical ability. We present these findings to broaden the definition of improvement in embodied AI passed increasingly complex models. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment

Code

Training

To train the predator and prey, run the following command:

python train.py --planning PLANNING --speed SPEED --vision VISION

Planning has the options of ['low', 'mid', 'high'].
Speed has the options of ['veryslow', 'slow', 'average', 'fast', 'veryfast'].
Vision has the options of ['short', 'medium', 'long'].

So an example command looks like this:

python train.py --planning high --speed average --vision long

Prey and Predator weights will save every 1000 gradient updates under a folder of the form log/planning_high_vision_long_speed_average (as an example corresponding to the example train command)

Evaluation

Our evaluation metric is the number of times that the predator is able to catch the prey in 10,000 steps. The location of the prey is randomly reset after it is caught by the predator (or after 400 steps to avoid outlier episodes).

To evaluate the training run, use the command:

python eval.py --prey-weights ./PATH/TO/PREY/WEIGHTS --predator-weights ./PATH/TO/PREY/WEIGHTS --speed fast --vision short --planning high

which will output a string of the form:

Number of prey caught in 10,000 steps is NUMBER

To visualize a video of the evaluation run, use the flag --video

Prerequisite packages can be found in requirements.txt

If you found this repository useful, please consider citing:

@article{pratt2022introspective,
  title={The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents},
  author={Pratt, Sarah and Weihs, Luca and Farhadi, Ali},
  journal={arXiv preprint arXiv:2201.00411},
  year={2022}
}
A clean and scalable template to kickstart your deep learning project 🚀 ⚡ 🔥

Lightning-Hydra-Template A clean and scalable template to kickstart your deep learning project 🚀 ⚡ 🔥 Click on Use this template to initialize new re

Hyunsoo Cho 1 Dec 20, 2021
Research Artifact of USENIX Security 2022 Paper: Automated Side Channel Analysis of Media Software with Manifold Learning

Manifold-SCA Research Artifact of USENIX Security 2022 Paper: Automated Side Channel Analysis of Media Software with Manifold Learning The repo is org

Yuanyuan Yuan 172 Dec 29, 2022
Face Alignment using python

Face Alignment Face Alignment using python Input Image Aligned Face Aligned Face Aligned Face Input Image Aligned Face Input Image Aligned Face Instal

Sajjad Aemmi 28 Nov 23, 2022
A repository for interferometer controller code.

dses-interferometer-controller A repository for interferometer controller code, hardware, and simulations. See dses.science for more information on th

Eli Reed 1 Jan 17, 2022
An API-first distributed deployment system of deep learning models using timeseries data to analyze and predict systems behaviour

Gordo Building thousands of models with timeseries data to monitor systems. Table of content About Examples Install Uninstall Developer manual How to

Equinor 26 Dec 27, 2022
Code for MSc Quantitative Finance Dissertation

MSc Dissertation Code ReadMe Sector Volatility Prediction Performance Using GARCH Models and Artificial Neural Networks Curtis Nybo MSc Quantitative F

2 Dec 01, 2022
This is the pytorch implementation for the paper: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation, which is accepted to ICCV2021.

GMPQ: Generalizable Mixed-Precision Quantization via Attribution Rank Preservation This is the pytorch implementation for the paper: Generalizable Mix

18 Sep 02, 2022
Augmented Traffic Control: A tool to simulate network conditions

Augmented Traffic Control Full documentation for the project is available at http://facebook.github.io/augmented-traffic-control/. Overview Augmented

Meta Archive 4.3k Jan 08, 2023
Code accompanying "Dynamic Neural Relational Inference" from CVPR 2020

Code accompanying "Dynamic Neural Relational Inference" This codebase accompanies the paper "Dynamic Neural Relational Inference" from CVPR 2020. This

Colin Graber 48 Dec 23, 2022
PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems

PowerGridworld provides users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training fr

National Renewable Energy Laboratory 37 Dec 17, 2022
Multiview Dataset Toolkit

Multiview Dataset Toolkit Using multi-view cameras is a natural way to obtain a complete point cloud. However, there is to date only one multi-view 3D

11 Dec 22, 2022
:boar: :bear: Deep Learning based Python Library for Stock Market Prediction and Modelling

bulbea "Deep Learning based Python Library for Stock Market Prediction and Modelling." Table of Contents Installation Usage Documentation Dependencies

Achilles Rasquinha 1.8k Jan 05, 2023
Fast Neural Style for Image Style Transform by Pytorch

FastNeuralStyle by Pytorch Fast Neural Style for Image Style Transform by Pytorch This is famous Fast Neural Style of Paper Perceptual Losses for Real

Bengxy 81 Sep 03, 2022
A model that attempts to learn and benefit from data collected on card counting.

A model that attempts to learn and benefit from data collected on card counting. A decision tree like model is built to win more often than loose and increase the bet of the player appropriately to c

1 Dec 17, 2021
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

The first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitecture design and Training techniques towards diverse noises.

132 Dec 23, 2022
Repository for the COLING 2020 paper "Explainable Automated Fact-Checking: A Survey."

Explainable Fact Checking: A Survey This repository and the accompanying webpage contain resources for the paper "Explainable Fact Checking: A Survey"

Neema Kotonya 42 Nov 17, 2022
Feature board for ERPNext

ERPNext Feature Board Feature board for ERPNext Development Prerequisites k3d kubectl helm bench Install K3d Cluster # export K3D_FIX_CGROUPV2=1 # use

Revant Nandgaonkar 16 Nov 09, 2022
Using multidimensional LSTM neural networks to create a forecast for Bitcoin price

Multidimensional LSTM BitCoin Time Series Using multidimensional LSTM neural networks to create a forecast for Bitcoin price. For notes around this co

Jakob Aungiers 318 Dec 14, 2022
RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds

RipsNet: a general architecture for fast and robust estimation of the persistent homology of point clouds This repository contains the code asscoiated

Felix Hensel 14 Dec 12, 2022
Lite-HRNet: A Lightweight High-Resolution Network

LiteHRNet Benchmark 🔥 🔥 Based on MMsegmentation 🔥 🔥 Cityscapes FCN resize concat config mIoU last mAcc last eval last mIoU best mAcc best eval bes

16 Dec 12, 2022