From d7c171321818cb42f77187f193721b6a333da188 Mon Sep 17 00:00:00 2001 From: Alessandro <aleite@lisn.fr> Date: Wed, 22 Sep 2021 16:52:22 +0200 Subject: [PATCH] Add the name of the environments --- README.md | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 4da1a06..339f740 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,8 @@ A python implementation of symbolic policy for interpretable reinforcement learn ### Installing dependencies - clone this repo - install with ` python -m pip install -r requirement.txt ` for base installation (no pygraphiz) -- install with ` python -m pip install -r requirement_with_pygrphivz.txt ` if you want to visualize program easily +- install with ` python -m pip install -r requirement_with_pygrphivz.txt ` if you want to visualize program easily +- install with `conda env create -f environment.yml` if you want to create a separate python environment with all the dependencies ## How to use ### Core functions @@ -73,3 +74,18 @@ seed: #set seed for random ## See the result Once an experiment is finished, you can see inspect results like in `tutorial.ipynb`. This notebook show how to see and run an individual from a saved population. + +## Environments + +| **Environment** | **Name** | +|-----------------------|-------------------------------------| +| Cartpole | CartPole-v1 | +| Acrobot | Acrobot-v1 | +| MountainCar | MountainCarContinuous-v0 | +| Pendulum | Pendulum-v0 | +| InvDoublePend | InvertedDoublePendulumBulletEnv-v0 | +| InvPendSwingUp | InvertedPendulumSwingupBulletEnv-v0 | +| LunarLander | LunarLanderContinuous-v2 | +| BipedalWalker | BipedalWalker-v3 | +| BipedalWalkerHardCore | | +| Hopper | HopperBulletEnv-v0 | -- GitLab