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

Automatic caption evaluation metric based on typicality analysis.

An OpenAI-Gym Package for Training and Testing Reinforcement Learning algorithms with OpenSim Models

Implementation of BI-RADS-BERT & The Advantages of Section Tokenization.

T2F: text to face generation using Deep Learning

[AAAI2022] Source code for our paper《Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning》

Quick program made to generate alpha and delta tables for Hidden Markov Models

Using multidimensional LSTM neural networks to create a forecast for Bitcoin price

Binary Stochastic Neurons in PyTorch

DrQ-v2: Improved Data-Augmented Reinforcement Learning

A new benchmark for Icon Question Answering (IconQA) and a large-scale icon dataset Icon645.

Unbalanced Feature Transport for Exemplar-based Image Translation (CVPR 2021)

STBP is a way to train SNN with datasets by Backward propagation.

InsCLR: Improving Instance Retrieval with Self-Supervision

A TensorFlow implementation of DeepMind's WaveNet paper

Sample and Computation Redistribution for Efficient Face Detection

Chainer implementation of recent GAN variants

Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations

State-to-Distribution (STD) Model

Powerful unsupervised domain adaptation method for dense retrieval.

Import Python modules from dicts and JSON formatted documents.