This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Last update: Jul 18, 2022

Overview

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay

This is the official implementation of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay" (PRICAI 2021).

Pre-requisites

python==3.6.8
gym==0.12.5
mujoco-py==2.0.2.0
tensorflow==1.13.1

Installation

Install the OpenMPI:

sudo apt-get install openmpi-bin openmpi-doc libopenmpi-dev

Install the required python packages.
Install baseline:

pip install -e .

Usage

Enter to the specific location:

cd ./baselines/her/experiment

The scripts for FetchEnv:

python train.py --env_name FetchPush-v1 --clip_div=0.001 --use_kdpp True --prioritization diversity --seed 0 --n_epochs 50 --num_cpu 16 --logdir logs/fetchpushv1/cpu16ep50/alg=DDPG+DTGSH=/r0 --logging True
python train.py --env_name FetchPickAndPlace-v1 --clip_div=0.001 --use_kdpp True --prioritization diversity --seed 0 --n_epochs 50 --num_cpu 16 --logdir logs/fetchpickv1/cpu16ep50/alg=DDPG+DTGSH=/r0 --logging True

The scripts for HandEnv:

python train.py --env_name HandManipulateEggFull-v0 --use_kdpp True  --prioritization diversity --seed 0 --goal_type full --sigma 0.1 --n_epochs 50 --num_cpu 16 --logdir logs/handegg1/cpu16ep50/alg=DDPG+DTGSH=/r0 --logging True
python train.py --env_name HandManipulateBlockRotateXYZ-v0 --use_kdpp True  --prioritization diversity --seed 0 --goal_type rotate --sigma 0.1 --n_epochs 50 --num_cpu 16 --logdir logs/handblock1/cpu16ep50/alg=DDPG+DTGSH=/r0 --logging True
python train.py --env_name HandManipulatePenRotate-v0 --use_kdpp True --prioritization diversity --seed 0 --goal_type rotate --sigma 0.1 --n_epochs 50 --num_cpu 16 --logdir logs/handpen1/cpu16ep50/alg=DDPG+DTGSH=/r0 --logging True

Acknowledgements

@ruizhaogit for Priority-based Experience Replay
@openai for Baselines
@satwik77 for Original DPP Implementation

This is the official code of our paper "Diversity-based Trajectory and Goal Selection with Hindsight Experience Relay" (PRICAI 2021)

Related tags

Overview

Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay

Pre-requisites

Installation

Usage

Acknowledgements

Owner

Tianhong Dai

Code for reproducing our paper: LMSOC: An Approach for Socially Sensitive Pretraining

📚 A collection of all the Deep Learning Metrics that I came across which are not accuracy/loss.

DyNet: The Dynamic Neural Network Toolkit

Official Implementation and Dataset of "PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency", CVPR 2021

A deep learning network built with TensorFlow and Keras to classify gender and estimate age.

TinyML Cookbook, published by Packt

AI Based Smart Exam Proctoring Package

MINOS: Multimodal Indoor Simulator

Learning the Beauty in Songs: Neural Singing Voice Beautifier; ACL 2022 (Main conference); Official code

A list of all named GANs!

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers (arXiv2021)

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel

Automatic Differentiation Multipole Moment Molecular Forcefield

The code uses SegFormer for Semantic Segmentation on Drone Dataset.

[ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization

Transfer SemanticKITTI labeles into other dataset/sensor formats.

Ipython notebook presentations for getting starting with basic programming, statistics and machine learning techniques

Dynamica causal Bayesian optimisation

PyTorch Implementation of our paper Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation

pytorch implementation of "Contrastive Multiview Coding", "Momentum Contrast for Unsupervised Visual Representation Learning", and "Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination"