Anonymous implementation of KSL

Last update: Nov 10, 2021

Related tags

Deep Learning ksl

Overview

k-Step Latent (KSL)

Implementation of k-Step Latent (KSL) in PyTorch.

Representation Learning for Data-Efficient Reinforcement Learning

[Paper]

Code is built on top of the DrQ repo from Denis Yarats.

Getting Started

First, create and activate conda env:

conda env create -f conda_env.yml

conda activate ksl

This repo relies on environments from DMControl, and therefore assumes that you can run MuJoCo.

From within ./ksl, simply run:

python train.py

Altering training schemes can be done by feeding additional args, such as:

python train.py env=cheetah_run lr=2e-4

For a full list of customizable args, see ./ksl/configs.yaml.

Observing Runs

Just as in the DrQ repo, train.py will produce the runs folder, where all the outputs are going to be stored including train/eval logs, tensorboard blobs, and evaluation episode videos. To launch tensorboard run

tensorboard --logdir runs

The console output is also available in a form:

| train | E: 5 | S: 5000 | R: 11.4359 | D: 66.8 s | BR: 0.0581 | ALOSS: -1.0640 | CLOSS: 0.0996 | TLOSS: -23.1683 | TVAL: 0.0945 | AENT: 3.8132

a training entry decodes as

train - training episode
E - total number of episodes
S - total number of environment steps
R - episode return
D - duration in seconds
BR - average reward of a sampled batch
ALOSS - average loss of the actor
CLOSS - average loss of the critic
TLOSS - average loss of the temperature parameter
TVAL - the value of temperature
AENT - the actor's entropy

while an evaluation entry

| eval  | E: 20 | S: 20000 | R: 10.9356

contains

E - evaluation was performed after E episodes
S - evaluation was performed after S environment steps
R - average episode return computed over `num_eval_episodes` (usually 10)

Anonymous implementation of KSL

Related tags

Overview

k-Step Latent (KSL)

Getting Started

Observing Runs

Owner

Code for the paper "Improved Techniques for Training GANs"

Object detection evaluation metrics using Python.

Image super-resolution through deep learning

Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

Official implementation for paper: Feature-Style Encoder for Style-Based GAN Inversion

[SIGGRAPH Asia 2019] Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning

[CVPR2021] The source code for our paper 《Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning》.

A 2D Visual Localization Framework based on Essential Matrices [ICRA2020]

Back to Basics: Efficient Network Compression via IMP

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

Beyond Image to Depth: Improving Depth Prediction using Echoes (CVPR 2021)

Maximum Spatial Perturbation for Image-to-Image Translation (Official Implementation)

PyTorch implementation of Pointnet2/Pointnet++

Implementation of the ICCV'21 paper Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

Code of the paper "Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition"

Recovering Brain Structure Network Using Functional Connectivity

Transfer Learning library for Deep Neural Networks.

《Geo Word Clouds》paper implementation

Snscrape-jsonl-urls-extractor - Extracts urls from jsonl produced by snscrape

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services