Code for "Unsupervised State Representation Learning in Atari"

Overview

Unsupervised State Representation Learning in Atari

Ankesh Anand*, Evan Racah*, Sherjil Ozair*, Yoshua Bengio, Marc-Alexandre Côté, R Devon Hjelm

This repo provides code for the benchmark and techniques introduced in the paper Unsupervised State Representation Learning in Atari

Install

AtariARI Wrapper

You can do a minimal install to get just the AtariARI (Atari Annotated RAM Interface) wrapper by doing:

pip install 'gym[atari]'
pip install git+git://github.com/mila-iqia/atari-representation-learning.git

This just requires gym[atari] and it gives you the ability to play around with the AtariARI wrapper. If you want to use the code for training representation learning methods and probing them, you will need a full installation:

Full installation (AtariARI Wrapper + Training & Probing Code)

# PyTorch and scikit learn
conda install pytorch torchvision -c pytorch
conda install scikit-learn

# Baselines for Atari preprocessing
# Tensorflow is a dependency, but you don't need to install the GPU version
conda install tensorflow
pip install git+git://github.com/openai/baselines

# pytorch-a2c-ppo-acktr for RL utils
pip install git+git://github.com/ankeshanand/pytorch-a2c-ppo-acktr-gail

# Clone and install our package
pip install -r requirements.txt
pip install git+git://github.com/mila-iqia/atari-representation-learning.git

Usage

Atari Annotated RAM Interface (AtariARI):

AtariARI exposes the ground truth labels for different state variables for each observation. We have made AtariARI available as a Gym wrapper, to use it simply wrap an Atari gym env with AtariARIWrapper.

import gym
from atariari.benchmark.wrapper import AtariARIWrapper
env = AtariARIWrapper(gym.make('MsPacmanNoFrameskip-v4'))
obs = env.reset()
obs, reward, done, info = env.step(1)

Now, info is a dictionary of the form:

{'ale.lives': 3,
 'labels': {'enemy_sue_x': 88,
  'enemy_inky_x': 88,
  'enemy_pinky_x': 88,
  'enemy_blinky_x': 88,
  'enemy_sue_y': 80,
  'enemy_inky_y': 80,
  'enemy_pinky_y': 80,
  'enemy_blinky_y': 50,
  'player_x': 88,
  'player_y': 98,
  'fruit_x': 0,
  'fruit_y': 0,
  'ghosts_count': 3,
  'player_direction': 3,
  'dots_eaten_count': 0,
  'player_score': 0,
  'num_lives': 2}}

Note: In our experiments, we use additional preprocessing for Atari environments mainly following Minh et. al, 2014. See atariari/benchmark/envs.py for more info!

If you want the raw RAM annotations (which parts of ram correspond to each state variable), check out atariari/benchmark/ram_annotations.py

Probing


⚠️ Important ⚠️ : The RAM labels are meant for full-sized Atari observations (210 * 160). Probing results won't be accurate if you downsample the observations.

We provide an interface for the included probing tasks.

First, get episodes for train, val and, test:

from atariari.benchmark.episodes import get_episodes

tr_episodes, val_episodes,\
tr_labels, val_labels,\
test_episodes, test_labels = get_episodes(env_name="PitfallNoFrameskip-v4", 
                                     steps=50000, 
                                     collect_mode="random_agent")

Then probe them using ProbeTrainer and your encoder (my_encoder):

from atariari.benchmark.probe import ProbeTrainer

probe_trainer = ProbeTrainer(my_encoder, representation_len=my_encoder.feature_size)
probe_trainer.train(tr_episodes, val_episodes,
                     tr_labels, val_labels,)
final_accuracies, final_f1_scores = probe_trainer.test(test_episodes, test_labels)

To see how we use ProbeTrainer, check out scripts/run_probe.py

Here is an example of my_encoder:

# get your encoder
import torch.nn as nn
import torch
class MyEncoder(nn.Module):
    def __init__(self, input_channels, feature_size):
        super().__init__()
        self.feature_size = feature_size
        self.input_channels = input_channels
        self.final_conv_size = 64 * 9 * 6
        self.cnn = nn.Sequential(
            nn.Conv2d(input_channels, 32, 8, stride=4),
            nn.ReLU(),
            nn.Conv2d(32, 64, 4, stride=2),
            nn.ReLU(),
            nn.Conv2d(64, 128, 4, stride=2),
            nn.ReLU(),
            nn.Conv2d(128, 64, 3, stride=1),
            nn.ReLU()
        )
        self.fc = nn.Linear(self.final_conv_size, self.feature_size)

    def forward(self, inputs):
        x = self.cnn(inputs)
        x = x.view(x.size(0), -1)
        return self.fc(x)
        

my_encoder = MyEncoder(input_channels=1,feature_size=256)
# load in weights
my_encoder.load_state_dict(torch.load(open("path/to/my/weights.pt", "rb")))

Spatio-Temporal DeepInfoMax:

src/ contains implementations of several representation learning methods, along with ST-DIM. Here's a sample usage:

python -m scripts.run_probe --method infonce-stdim --env-name {env_name}

where env_name is of the form {game}NoFrameskip-v4, such as PongNoFrameskip-v4

Citation

@article{anand2019unsupervised,
  title={Unsupervised State Representation Learning in Atari},
  author={Anand, Ankesh and Racah, Evan and Ozair, Sherjil and Bengio, Yoshua and C{\^o}t{\'e}, Marc-Alexandre and Hjelm, R Devon},
  journal={arXiv preprint arXiv:1906.08226},
  year={2019}
}
Owner
Mila
Quebec Artificial Intelligence Institute
Mila
JAXMAPP: JAX-based Library for Multi-Agent Path Planning in Continuous Spaces

JAXMAPP: JAX-based Library for Multi-Agent Path Planning in Continuous Spaces JAXMAPP is a JAX-based library for multi-agent path planning (MAPP) in c

OMRON SINIC X 24 Dec 28, 2022
An image classification app boilerplate to serve your deep learning models asap!

Image 🖼 Classification App Boilerplate Have you been puzzled by tons of videos, blogs and other resources on the internet and don't know where and ho

Smaranjit Ghose 27 Oct 06, 2022
Introduction to Statistics and Basics of Mathematics for Data Science - The Hacker's Way

HackerMath for Machine Learning “Study hard what interests you the most in the most undisciplined, irreverent and original manner possible.” ― Richard

Amit Kapoor 1.4k Dec 22, 2022
[CVPR 2022] Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement

Back To Reality: Weak-supervised 3D Object Detection with Shape-guided Label Enhancement Announcement 🔥 We have not tested the code yet. We will fini

Xiuwei Xu 7 Oct 30, 2022
Keras Realtime Multi-Person Pose Estimation - Keras version of Realtime Multi-Person Pose Estimation project

This repository has become incompatible with the latest and recommended version of Tensorflow 2.0 Instead of refactoring this code painfully, I create

M Faber 769 Dec 08, 2022
Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution

FAU Implementation of the paper: Facial Action Unit Intensity Estimation via Semantic Correspondence Learning with Dynamic Graph Convolution. Yingruo

Evelyn 78 Nov 29, 2022
Official pytorch code for "APP: Anytime Progressive Pruning"

APP: Anytime Progressive Pruning Diganta Misra1,2,3, Bharat Runwal2,4, Tianlong Chen5, Zhangyang Wang5, Irina Rish1,3 1 Mila - Quebec AI Institute,2 L

Landskape AI 12 Nov 22, 2022
D-NeRF: Neural Radiance Fields for Dynamic Scenes

D-NeRF: Neural Radiance Fields for Dynamic Scenes [Project] [Paper] D-NeRF is a method for synthesizing novel views, at an arbitrary point in time, of

Albert Pumarola 291 Jan 02, 2023
Machine Learning Platform for Kubernetes

Reproduce, Automate, Scale your data science. Welcome to Polyaxon, a platform for building, training, and monitoring large scale deep learning applica

polyaxon 3.2k Dec 23, 2022
Permute Me Softly: Learning Soft Permutations for Graph Representations

Permute Me Softly: Learning Soft Permutations for Graph Representations

Giannis Nikolentzos 7 Jul 10, 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
Synthetic Humans for Action Recognition, IJCV 2021

SURREACT: Synthetic Humans for Action Recognition from Unseen Viewpoints Gül Varol, Ivan Laptev and Cordelia Schmid, Andrew Zisserman, Synthetic Human

Gul Varol 59 Dec 14, 2022
An investigation project for SISR.

SISR-Survey An investigation project for SISR. This repository is an official project of the paper "From Beginner to Master: A Survey for Deep Learnin

Juncheng Li 79 Oct 20, 2022
Preparation material for Dropbox interviews

Dropbox-Onsite-Interviews A guide for the Dropbox onsite interview! The Dropbox interview question bank is very small. The bank has been in a Chinese

386 Dec 31, 2022
yolov5目标检测模型的知识蒸馏(基于响应的蒸馏)

代码地址: https://github.com/Sharpiless/yolov5-knowledge-distillation 教师模型: python train.py --weights weights/yolov5m.pt \ --cfg models/yolov5m.ya

52 Dec 04, 2022
Python framework for Stochastic Differential Equations modeling

SDElearn: a Python package for SDE modeling This package implements functionalities for working with Stochastic Differential Equations models (SDEs fo

4 May 10, 2022
Joint deep network for feature line detection and description

SOLD² - Self-supervised Occlusion-aware Line Description and Detection This repository contains the implementation of the paper: SOLD² : Self-supervis

Computer Vision and Geometry Lab 427 Dec 27, 2022
A no-BS, dead-simple training visualizer for tf-keras

A no-BS, dead-simple training visualizer for tf-keras TrainingDashboard Plot inter-epoch and intra-epoch loss and metrics within a jupyter notebook wi

Vibhu Agrawal 3 May 28, 2021
PyTorch Implementation of CycleGAN and SSGAN for Domain Transfer (Minimal)

MNIST-to-SVHN and SVHN-to-MNIST PyTorch Implementation of CycleGAN and Semi-Supervised GAN for Domain Transfer. Prerequites Python 3.5 PyTorch 0.1.12

Yunjey Choi 401 Dec 30, 2022