Implementation of the ALPHAMEPOL algorithm, presented in Unsupervised Reinforcement Learning in Multiple Environments.

Overview

ALPHAMEPOL

This repository contains the implementation of the ALPHAMEPOL algorithm, presented in Unsupervised Reinforcement Learning in Multiple Environments.

Installation

In order to use this codebase you need to work with a Python version >= 3.6. Moreover, you need to have a working setup of Mujoco with a valid Mujco license. To setup Mujoco, have a look here. To avoid any conflict with your existing Python setup, and to keep this project self-contained, it is suggested to work in a virtual environment with virtualenv. To install virtualenv:

pip install --upgrade virtualenv

Create a virtual environment, activate it and install the requirements:

virtualenv venv
source venv/bin/activate
pip install -r requirements.txt

Usage

Unsupervised Pre-Training

To reproduce the Unsupervised Pre-Training experiments in the paper, run:

./scripts/exploration/[gridworld_with_slope.sh | multigrid.sh | ant.sh | minigrid.sh]

Supervised Fine-Tuning

To reproduce the Supervised Fine-Tuning experiments, run:

./scripts/goal_rl/[gridworld_with_slope.sh | multigrid.sh | ant.sh | minigrid.sh]

By default, this will launch TRPO with ALPHAMEPOL initialization. To launch TRPO with a random initialization, simply omit the policy_init argument in the scripts.

Moreover, note that the scripts for the GridWorld with Slope and MultiGrid experiments have the argument num_goals = 50, meaning that the training will be performed with one goal at a time. If you want to speed up the process, you can use several processes (ideally one for each goal), by passing as argument num_goals = 1 and changing incrementally the seed. As regards the Ant and MiniGrid experiments, since the goals are predefined, you can also set the goal_index argument to specify a goal (from 0 to 7 and from 0 to 12 respectively).

Results Visualization

Once launched, each experiment will log statistics in the results folder. You can visualize everything by launching tensorboard targeting that directory:

python -m tensorboard.main --logdir=./results --port 8080

and visiting the board at http://localhost:8080.

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations 3D-aware Image Synthesis via Learning Structural and Textura

GenForce: May Generative Force Be with You 116 Dec 26, 2022
Reinforcement learning library in JAX.

Reinforcement learning library in JAX.

Yicheng Luo 96 Oct 30, 2022
ICRA 2021 - Robust Place Recognition using an Imaging Lidar

Robust Place Recognition using an Imaging Lidar A place recognition package using high-resolution imaging lidar. For best performance, a lidar equippe

Tixiao Shan 293 Dec 27, 2022
Applying PVT to Semantic Segmentation

Applying PVT to Semantic Segmentation Here, we take MMSegmentation v0.13.0 as an example, applying PVTv2 to SemanticFPN. For details see Pyramid Visio

35 Nov 30, 2022
Localized representation learning from Vision and Text (LoVT)

Localized Vision-Text Pre-Training Contrastive learning has proven effective for pre- training image models on unlabeled data and achieved great resul

Philip Müller 10 Dec 07, 2022
PyTorch Implementation of "Light Field Image Super-Resolution with Transformers"

LFT PyTorch implementation of "Light Field Image Super-Resolution with Transformers", arXiv 2021. [pdf]. Contributions: We make the first attempt to a

Squidward 62 Nov 28, 2022
Multiple paper open-source codes of the Microsoft Research Asia DKI group

📫 Paper Code Collection (MSRA DKI Group) This repo hosts multiple open-source codes of the Microsoft Research Asia DKI Group. You could find the corr

Microsoft 249 Jan 08, 2023
Official PyTorch implementation of the Fishr regularization for out-of-distribution generalization

Fishr: Invariant Gradient Variances for Out-of-distribution Generalization Official PyTorch implementation of the Fishr regularization for out-of-dist

62 Dec 22, 2022
SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks Molecular interaction networks are powerful resources for the discovery. While dee

Kexin Huang 49 Oct 15, 2022
Simple reimplemetation experiments about FcaNet

FcaNet-CIFAR An implementation of the paper FcaNet: Frequency Channel Attention Networks on CIFAR10/CIFAR100 dataset. how to run Code: python Cifar.py

76 Feb 04, 2021
A PyTorch-based Semi-Supervised Learning (SSL) Codebase for Pixel-wise (Pixel) Vision Tasks

PixelSSL is a PyTorch-based semi-supervised learning (SSL) codebase for pixel-wise (Pixel) vision tasks. The purpose of this project is to promote the

Zhanghan Ke 255 Dec 11, 2022
A 1.3B text-to-image generation model trained on 14 million image-text pairs

minDALL-E on Conceptual Captions minDALL-E, named after minGPT, is a 1.3B text-to-image generation model trained on 14 million image-text pairs for no

Kakao Brain 604 Dec 14, 2022
Official PyTorch implementation of "RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on" (IJCAI-ECAI 2022)

RMGN-VITON RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on In IJCAI-ECAI 2022(short oral). [Paper] [Supplementary Material] Abstra

27 Dec 01, 2022
Machine Learning Model deployment for Container (TensorFlow Serving)

try_tf_serving ├───dataset │ ├───testing │ │ ├───paper │ │ ├───rock │ │ └───scissors │ └───training │ ├───paper │ ├───rock

Azhar Rizki Zulma 5 Jan 07, 2022
Alphabetical Letter Recognition

DecisionTrees-Image-Classification Alphabetical Letter Recognition In these demo we are using "Decision Trees" Our database is composed by Learning Im

Mohammed Firass 4 Nov 30, 2021
Train CPPNs as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images.

cppn-gan-vae tensorflow Train Compositional Pattern Producing Network as a Generative Model, using Generative Adversarial Networks and Variational Aut

hardmaru 343 Dec 29, 2022
Certis - Certis, A High-Quality Backtesting Engine

Certis - Backtesting For y'all Certis is a powerful, lightweight, simple backtes

Yeachan-Heo 46 Oct 30, 2022
Human Pose Detection on EdgeTPU

Coral PoseNet Pose estimation refers to computer vision techniques that detect human figures in images and video, so that one could determine, for exa

google-coral 476 Dec 31, 2022
This implements one of result networks from Large-scale evolution of image classifiers

Exotic structured image classifier This implements one of result networks from Large-scale evolution of image classifiers by Esteban Real, et. al. Req

54 Nov 25, 2022
Fuzzy Overclustering (FOC)

Fuzzy Overclustering (FOC) In real-world datasets, we need consistent annotations between annotators to give a certain ground-truth label. However, in

2 Nov 08, 2022