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...

Full description

Bibliographic Details
Main Authors: Wah Loon Keng, Graesser, Laura, TASSEL, Pierre, Allan-Avatar1, Snyk Bot, Gillen, Sean, Rahim16, Cvitkovic, Milan, Schock, Michael, Ayala, Angel
Format: Article in Journal/Newspaper
Language:unknown
Published: Zenodo 2020
Subjects:
Orca
Online Access:https://dx.doi.org/10.5281/zenodo.3751787
https://zenodo.org/record/3751787
Description
Summary: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.

Similar Items