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

STMTrack: Template-free Visual Tracking with Space-time Memory Networks

Worktory is a python library created with the single purpose of simplifying the inventory management of network automation scripts.

A list of awesome PyTorch scholarship articles, guides, blogs, courses and other resources.

CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching（CVPR2021）

Source code for the paper "Periodic Traveling Waves in an Integro-Difference Equation With Non-Monotonic Growth and Strong Allee Effect"

code and models for "Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation"

Reading list for research topics in Masked Image Modeling

Pytorch implementation of SimSiam Architecture

A python script to dump all the challenges locally of a CTFd-based Capture the Flag.

Object Detection and Multi-Object Tracking

This repo contains the implementation of YOLOv2 in Keras with Tensorflow backend.

A Parameter-free Deep Embedded Clustering Method for Single-cell RNA-seq Data

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System

[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

This is the repository for CVPR2021 Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales

Rank1 Conversation Emotion Detection Task

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency[ECCV 2020]

Luminous is a framework for testing the performance of Embodied AI (EAI) models in indoor tasks.

Official pytorch implementation of the IrwGAN for unaligned image-to-image translation