Codebase for the self-supervised goal reaching benchmark introduced in the LEXA paper

Overview

LEXA Benchmark

Codebase for the self-supervised goal reaching benchmark introduced in the LEXA paper (Discovering and Achieving Goals via World Models, NeurIPS 2021).

Setup

Create the conda environment by running : conda env create -f environment.yml

Alternatively, you can update an existing conda environment by running : conda env update -f environment.yml

Modify the python path
export PYTHONPATH=

Export the following variables for rendering
export MUJOCO_RENDERER=egl; export MUJOCO_GL=egl

Please follow these instructions to install mujoco

Bibtex

If you find this code useful, please cite:

@misc{lexa2021,
    title={Discovering and Achieving Goals via World Models},
    author={Mendonca, Russell and Rybkin, Oleh and
    Daniilidis, Kostas and Hafner, Danijar and Pathak, Deepak},
    year={2021},
    Booktitle={NeurIPS}
}

Acknowledgements

This benchmark is built on top of the following environments: Adept, MetaWorld, and DeepMind Control Suite.

You might also like...
Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

UniSpeech The family of UniSpeech: UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR UniSpeech-

This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

Reinforcement-trading This project uses Reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can

Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent

Narya The Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent. This repository

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt
Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt

Feed forward VQGAN-CLIP model, where the goal is to eliminate the need for optimizing the latent space of VQGAN for each input prompt. This is done by

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

Angora Angora is a mutation-based coverage guided fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without s

 Learning Domain Invariant Representations in Goal-conditioned Block MDPs
Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Learning Domain Invariant Representations in Goal-conditioned Block MDPs Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jim

A computational optimization project towards the goal of gerrymandering the results of a hypothetical election in the UK.

A computational optimization project towards the goal of gerrymandering the results of a hypothetical election in the UK.

Group project for MFIN7036. Our goal is to predict firm profitability with text-based competition measures.

NLP_0-project Group project for MFIN7036. Our goal is to predict firm profitability with text-based competition measures1. We are a "democratic" and c

Codebase for the Summary Loop paper at ACL2020
Codebase for the Summary Loop paper at ACL2020

Summary Loop This repository contains the code for ACL2020 paper: The Summary Loop: Learning to Write Abstractive Summaries Without Examples. Training

Comments
  • Problem in distance function / success criterion for dmc walker

    Problem in distance function / success criterion for dmc walker

    I noticed a problem in the distance function when running experiments on the dmc_walker_walk task.

    from lexa_benchmark.envs.dmc import DmcEnv
    
    env = DmcEnv('walker_walk')
    final_state = [-0.56107332, 0.20019225, 0.6347682, 1.75441328, 0.00908487, 0.7944932, 0.74205822, -1.85826755, -0.79472572]
    env._compute_reward(goal_idx=9, pose=final_state)
    

    The above code will output (-0.6347682, 1.0) which means that the final distance to the goal is 0.6347682 and that the episode is considered successful.

    However, the final_state corresponds to the following observation: image

    and the goal is: image

    So we clearly see that the distance function and/or success threshold should be defined differently to assess whether the goal was achieved or not.

    opened by LinaMezghani 1
Owner
Oleg Rybkin
Ph.D. student with Kostas Daniilidis. I work on making machines think about the future.
Oleg Rybkin
A benchmark dataset for mesh multi-label-classification based on cube engravings introduced in MeshCNN

Double Cube Engravings This script creates a dataset for multi-label mesh clasification, with an intentionally difficult setup for point cloud classif

Yotam Erel 1 Nov 30, 2021
The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with

SpaceML 92 Nov 30, 2022
Utility tools for the "Divide and Remaster" dataset, introduced as part of the Cocktail Fork problem paper

Divide and Remaster Utility Tools Utility tools for the "Divide and Remaster" dataset, introduced as part of the Cocktail Fork problem paper The DnR d

Darius Petermann 46 Dec 11, 2022
A weakly-supervised scene graph generation codebase. The implementation of our CVPR2021 paper ``Linguistic Structures as Weak Supervision for Visual Scene Graph Generation''

README.md shall be finished soon. WSSGG 0 Overview 1 Installation 1.1 Faster-RCNN 1.2 Language Parser 1.3 GloVe Embeddings 2 Settings 2.1 VG-GT-Graph

Keren Ye 35 Nov 20, 2022
This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

H3DS Dataset This repository contains the code for using the H3DS dataset introduced in H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction Access

Crisalix 72 Dec 10, 2022
A commany has recently introduced a new type of bidding, the average bidding, as an alternative to the bid given to the current maximum bidding

Business Problem A commany has recently introduced a new type of bidding, the average bidding, as an alternative to the bid given to the current maxim

Kübra Bilinmiş 1 Jan 15, 2022
This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay This is the official implementation of our paper "Diversity-based Traje

Tianhong Dai 6 Jul 18, 2022
[CVPR 2021] "The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models" Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Michael Carbin, Zhangyang Wang

The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models Codes for this paper The Lottery Tickets Hypo

VITA 59 Dec 28, 2022
Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models

Patch-Rotation(PatchRot) Patch Rotation: A Self-Supervised Auxiliary Task for Robustness and Accuracy of Supervised Models Submitted to Neurips2021 To

null 4 Jul 12, 2021