From 67884effa3e93f98a2531ea39768b90a07204cd6 Mon Sep 17 00:00:00 2001 From: gmollard <guillaume.mollard2@gmail.com> Date: Thu, 18 Jul 2019 21:19:55 +0000 Subject: [PATCH] Update README.md --- RLLib_training/README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/RLLib_training/README.md b/RLLib_training/README.md index 21665a5..7b48f57 100644 --- a/RLLib_training/README.md +++ b/RLLib_training/README.md @@ -2,6 +2,7 @@ This repository allows to run Rail Environment multi agent training with the RLL ## Installation: ```sh +pip install gym pip install ray pip install gin-config ``` @@ -57,7 +58,7 @@ More documentation on how to use gin-config can be found on the github repositor ## Run an example: To start a training on a 20X20 map, with different numbers of agents initialized at each episode, on can run the train_experiment.py script: ``` -python baselines/RLLib_training/train_experiment.py +python RLLib_training/train_experiment.py ``` This will load the gin config file in the folder `experiment_configs/config_examples`. -- GitLab