kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory
Resume mode #455 adds train@ resume mode and refactors the enjoy mode. See PR for detailed info. train@ usage example Specify train mode as train@{predir} , where {predir} is the data directory of the last training run, or simply use latest` to use the latest. e.g.: <code class="lang-bash&qu...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Zenodo
2020
|
Subjects: | |
Online Access: | https://dx.doi.org/10.5281/zenodo.3751787 https://zenodo.org/record/3751787 |
id |
ftdatacite:10.5281/zenodo.3751787 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.5281/zenodo.3751787 2023-05-15T17:53:53+02:00 kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory Wah Loon Keng Graesser, Laura TASSEL, Pierre Allan-Avatar1 Snyk Bot Gillen, Sean Rahim16 Cvitkovic, Milan Schock, Michael Ayala, Angel 2020 https://dx.doi.org/10.5281/zenodo.3751787 https://zenodo.org/record/3751787 unknown Zenodo https://github.com/kengz/SLM-Lab/tree/v4.2.0 https://github.com/kengz/SLM-Lab/tree/v4.2.0 https://dx.doi.org/10.5281/zenodo.1174529 Open Access info:eu-repo/semantics/openAccess Software SoftwareSourceCode article 2020 ftdatacite https://doi.org/10.5281/zenodo.3751787 https://doi.org/10.5281/zenodo.1174529 2021-11-05T12:55:41Z Resume mode #455 adds train@ resume mode and refactors the enjoy mode. See PR for detailed info. train@ usage example Specify train mode as train@{predir} , where {predir} is the data directory of the last training run, or simply use latest` to use the latest. e.g.: <code class="lang-bash">python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train # terminate run before its completion # optionally edit the spec file in a past-future-consistent manner # run resume with either of the commands: python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train@latest # or to use a specific run folder python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train@data/reinforce_cartpole_2020_04_13_232521 enjoy mode refactor The train@ resume mode API allows for the enjoy mode to be refactored. Both share similar syntax. Continuing with the example above, to enjoy a train model, we now use: <code class="lang-bash">python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole enjoy@data/reinforce_cartpole_2020_04_13_232521/reinforce_cartpole_t0_s0_spec.json Plotly and PyTorch update #453 updates Plotly to 4.5.4 and PyTorch to 1.3.1. #454 explicitly shuts down Plotly orca server after plotting to prevent zombie processes PPO batch size optimization #453 adds chunking to allow PPO to run on larger batch size by breaking up the forward loop. New OnPolicyCrossEntropy memory #446 adds a new OnPolicyCrossEntropy memory class. See PR for details. Credits to @ingambe. Article in Journal/Newspaper Orca DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
description |
Resume mode #455 adds train@ resume mode and refactors the enjoy mode. See PR for detailed info. train@ usage example Specify train mode as train@{predir} , where {predir} is the data directory of the last training run, or simply use latest` to use the latest. e.g.: <code class="lang-bash">python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train # terminate run before its completion # optionally edit the spec file in a past-future-consistent manner # run resume with either of the commands: python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train@latest # or to use a specific run folder python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole train@data/reinforce_cartpole_2020_04_13_232521 enjoy mode refactor The train@ resume mode API allows for the enjoy mode to be refactored. Both share similar syntax. Continuing with the example above, to enjoy a train model, we now use: <code class="lang-bash">python run_lab.py slm_lab/spec/benchmark/reinforce/reinforce_cartpole.json reinforce_cartpole enjoy@data/reinforce_cartpole_2020_04_13_232521/reinforce_cartpole_t0_s0_spec.json Plotly and PyTorch update #453 updates Plotly to 4.5.4 and PyTorch to 1.3.1. #454 explicitly shuts down Plotly orca server after plotting to prevent zombie processes PPO batch size optimization #453 adds chunking to allow PPO to run on larger batch size by breaking up the forward loop. New OnPolicyCrossEntropy memory #446 adds a new OnPolicyCrossEntropy memory class. See PR for details. Credits to @ingambe. |
format |
Article in Journal/Newspaper |
author |
Wah Loon Keng Graesser, Laura TASSEL, Pierre Allan-Avatar1 Snyk Bot Gillen, Sean Rahim16 Cvitkovic, Milan Schock, Michael Ayala, Angel |
spellingShingle |
Wah Loon Keng Graesser, Laura TASSEL, Pierre Allan-Avatar1 Snyk Bot Gillen, Sean Rahim16 Cvitkovic, Milan Schock, Michael Ayala, Angel kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
author_facet |
Wah Loon Keng Graesser, Laura TASSEL, Pierre Allan-Avatar1 Snyk Bot Gillen, Sean Rahim16 Cvitkovic, Milan Schock, Michael Ayala, Angel |
author_sort |
Wah Loon Keng |
title |
kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
title_short |
kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
title_full |
kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
title_fullStr |
kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
title_full_unstemmed |
kengz/SLM-Lab: Resume mode, Plotly and PyTorch update, OnPolicyCrossEntropy memory |
title_sort |
kengz/slm-lab: resume mode, plotly and pytorch update, onpolicycrossentropy memory |
publisher |
Zenodo |
publishDate |
2020 |
url |
https://dx.doi.org/10.5281/zenodo.3751787 https://zenodo.org/record/3751787 |
genre |
Orca |
genre_facet |
Orca |
op_relation |
https://github.com/kengz/SLM-Lab/tree/v4.2.0 https://github.com/kengz/SLM-Lab/tree/v4.2.0 https://dx.doi.org/10.5281/zenodo.1174529 |
op_rights |
Open Access info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.5281/zenodo.3751787 https://doi.org/10.5281/zenodo.1174529 |
_version_ |
1766161594202456064 |