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

Generative Autoregressive, Normalized Flows, VAEs, Score-based models (GANVAS)

DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

Riemannian Convex Potential Maps

Automatic detection and classification of Covid severity degree in LUS (lung ultrasound) scans

Segmentation models with pretrained backbones. PyTorch.

An easy way to build PyTorch datasets. Modularly build datasets and automatically cache processed results

A ssl analyzer which could analyzer target domain's certificate.

PyTorch code accompanying the paper "Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning" (NeurIPS 2021).

Density-aware Single Image De-raining using a Multi-stream Dense Network (CVPR 2018)

Similarity-based Gray-box Adversarial Attack Against Deep Face Recognition

Online Multi-Granularity Distillation for GAN Compression (ICCV2021)

BLEURT is a metric for Natural Language Generation based on transfer learning.

This project aims at providing a concise, easy-to-use, modifiable reference implementation for semantic segmentation models using PyTorch.

Linescanning - Package for (pre)processing of anatomical and (linescanning) fMRI data

An open source Jetson Nano baseboard and tools to design your own.

PyTorch implementation of our paper How robust are discriminatively trained zero-shot learning models?

Bottleneck Transformers for Visual Recognition

A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.

This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,