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

Gin provides a lightweight configuration framework for Python

Pytorch implementation of the unsupervised object discovery method LOST.

NIMA: Neural IMage Assessment

Joint detection and tracking model named DEFT, or ``Detection Embeddings for Tracking.

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Aesara is a Python library that allows one to define, optimize, and efficiently evaluate mathematical expressions involving multi-dimensional arrays.

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

Vit-ImageClassification - Pytorch ViT for Image classification on the CIFAR10 dataset

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

Transfer Learning Remote Sensing

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

DeepHawkeye is a library to detect unusual patterns in images using features from pretrained neural networks

Trajectory Prediction with Graph-based Dual-scale Context Fusion

Fast, Attemptable Route Planner for Navigation in Known and Unknown Environments

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

Everything's Talkin': Pareidolia Face Reenactment (CVPR2021)

Semi-Supervised Learning for Fine-Grained Classification