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

Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detection

CoRe: Contrastive Recurrent State-Space Models

Code for "Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks", CVPR 2021

Generative Exploration and Exploitation - This is an improved version of GENE.

Codes for "Template-free Prompt Tuning for Few-shot NER".

Joint project of the duo Hacker Ninjas

Predicting lncRNA–protein interactions based on graph autoencoders and collaborative training

Perform zero-order Hankel Transform for an 1D array (float or real valued).

Lowest memory consumption and second shortest runtime in NTIRE 2022 challenge on Efficient Super-Resolution

Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations. [2021]

Train SN-GAN with AdaBelief

🌳 A Python-inspired implementation of the Optimum-Path Forest classifier.

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021)

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

CrossMLP - The repository offers the official implementation of our BMVC 2021 paper (oral) in PyTorch.

Attention mechanism with MNIST dataset

N-Person-Check-Checker-Splitter - A calculator app use to divide checks

Official implementation for paper Render In-between: Motion Guided Video Synthesis for Action Interpolation

Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies

TensorFlow CNN for fast style transfer