Tackling Obstacle Tower Challenge using PPO & A2C combined with ICM.

Overview

Obstacle Tower Challenge using Deep Reinforcement Learning

Unity Obstacle Tower is a challenging realistic 3D, third person perspective and procedurally generated environment, which we use as the benchmark to test the performance of our deep RL models.

Proximal Policy Optimization (PPO) and Advantage Actor Critic (A2C), both combined with Intrinsic Curiosity Model (ICM), are implemented. We train our agent using both PPO and A2C while calculating several metrics such as loss function and reward to evaluate these two methods.

More details regarding this project can be viewed in our paper.

Dependencies

Requirements: see requirements.txt. We also require python 3.5+ and pip.

Install dependencies with pip install -r requirements.txt.

Download the environment at Obstacle Tower Github page here, unzip it and place it into the root of the project.

Training an agent

Run

Run python3 -m agent.learn. This will initialize training with default parameters and it will use A2C as a learning method.

Run python3 -m agent.learn -h to check all options and their description.

Visualization

Training can be visualized with TensorboardX.
After initial collection of observation stops and training starts, a log file that recording the data during the training process will be created in the runs/ file.

Run tensorboard --logdir runs/ . This will start server on localhost:6006 by default.

For example, you can run tensorboard --logdir runs/a2c to see the visualization results of a training process using the given a2c model.

Here is a screenshot of the visualization example:

Running the agent

Run python3 -m runner --model_name This will start inference mode with selected model.

Two pretrained sample models are placed in models/ directory. To check all available options run python3 -m runner -h.
Agent runs until in-game time runs up.

For example, you can run python -m runner --model_name model_a2c_750.bin using the given sample model.

Here is a screenshot of a single run:

Owner
Zhuoyu Feng
Zhuoyu Feng
Code for "3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop"

PyMAF This repository contains the code for the following paper: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop Hongwe

Hongwen Zhang 450 Dec 28, 2022
Manifold-Mixup implementation for fastai V2

Manifold Mixup Unofficial implementation of ManifoldMixup (Proceedings of ICML 19) for fast.ai (V2) based on Shivam Saboo's pytorch implementation of

Nestor Demeure 16 Jul 25, 2022
I3-master-layout - Simple master and stack layout script

Simple master and stack layout script | ------ | ----- | | | | | Ma

Tobias S 18 Dec 05, 2022
Code for testing various M1 Chip benchmarks with TensorFlow.

M1, M1 Pro, M1 Max Machine Learning Speed Test Comparison This repo contains some sample code to benchmark the new M1 MacBooks (M1 Pro and M1 Max) aga

Daniel Bourke 348 Jan 04, 2023
Dcf-game-infrastructure-public - Contains all the components necessary to run a DC finals (attack-defense CTF) game from OOO

dcf-game-infrastructure All the components necessary to run a game of the OOO DC

Order of the Overflow 46 Sep 13, 2022
VOneNet: CNNs with a Primary Visual Cortex Front-End

VOneNet: CNNs with a Primary Visual Cortex Front-End A family of biologically-inspired Convolutional Neural Networks (CNNs). VOneNets have the followi

The DiCarlo Lab at MIT 99 Dec 22, 2022
Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution

unfoldedVBA Unrolled Variational Bayesian Algorithm for Image Blind Deconvolution This repository contains the Pytorch implementation of the unrolled

Yunshi HUANG 2 Jul 10, 2022
Offline Reinforcement Learning with Implicit Q-Learning

Offline Reinforcement Learning with Implicit Q-Learning This repository contains the official implementation of Offline Reinforcement Learning with Im

Ilya Kostrikov 125 Dec 31, 2022
Recurrent Scale Approximation (RSA) for Object Detection

Recurrent Scale Approximation (RSA) for Object Detection Codebase for Recurrent Scale Approximation for Object Detection in CNN published at ICCV 2017

Yu Liu (Louis) 239 Dec 28, 2022
Official implementation of the paper 'High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network' in CVPR 2021

LPTN Paper | Supplementary Material | Poster High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network Ji

372 Dec 26, 2022
Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning Reference Abeßer, J. & Müller, M. Towards Audio Domain Adapt

Jakob Abeßer 2 Jul 06, 2022
COIN the currently largest dataset for comprehensive instruction video analysis.

COIN Dataset COIN is the currently largest dataset for comprehensive instruction video analysis. It contains 11,827 videos of 180 different tasks (i.e

86 Dec 28, 2022
TensorFlow Implementation of "Show, Attend and Tell"

Show, Attend and Tell Update (December 2, 2016) TensorFlow implementation of Show, Attend and Tell: Neural Image Caption Generation with Visual Attent

Yunjey Choi 902 Nov 29, 2022
One-line your code easily but still with the fun of doing so!

One-liner-iser One-line your code easily but still with the fun of doing so! Have YOU ever wanted to write one-line Python code, but don't have the sa

5 May 04, 2022
PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML)

pytorch-maml This is a PyTorch implementation of the supervised learning experiments from the paper Model-Agnostic Meta-Learning (MAML): https://arxiv

Kate Rakelly 516 Jan 05, 2023
Disentangled Face Attribute Editing via Instance-Aware Latent Space Search, accepted by IJCAI 2021.

Instance-Aware Latent-Space Search This is a PyTorch implementation of the following paper: Disentangled Face Attribute Editing via Instance-Aware Lat

67 Dec 21, 2022
🔥 Cannlytics-powered artificial intelligence 🤖

Cannlytics AI 🔥 Cannlytics-powered artificial intelligence 🤖 🏗️ Installation 🏃‍♀️ Quickstart 🧱 Development 🦾 Automation 💸 Support 🏛️ License ?

Cannlytics 3 Nov 11, 2022
Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation

SSWS-loss_function_based_on_MS-TCN Supervised Sliding Window Smoothing Loss Function Based on MS-TCN for Video Segmentation Supervised Sliding Window

3 Aug 03, 2022
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Advanced Image Manipulation Lab @ Samsung AI Center Moscow 4.7k Dec 31, 2022
Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Google Research 340 Jan 03, 2023