VedantDave/sac_ae_if
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Denis Yarats 2019-09-23 15:00:08 -04:00 committed by GitHub
parent f2e39f7a68
commit 7400ed0e17
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -1,6 +1,10 @@
# SAC+AE implementaiton in PyTorch # SAC+AE implementaiton in PyTorch
## Requirements ## Requirements
The simplest way to install all required dependencies is to create an anaconda environment by running:
```
conda env create -f conda_env.yml
```
## Instructions ## Instructions
To train an SAC+AE agent on the `cheetah run` task from image-based observations run: To train an SAC+AE agent on the `cheetah run` task from image-based observations run:
@ -13,7 +17,7 @@ python train.py \
--action_repeat 4 \ --action_repeat 4 \
--save_video \ --save_video \
--save_tb \ --save_tb \
--work_dir ./runs/cheetah_run/sac_ae \ --work_dir ./log \
--seed 1 --seed 1
``` ```
This will produce a folder (`./save`) by default, where all the output is going to be stored including train/eval logs, tensorboard blobs, evaluation videos, and model snapshots. It is possible to attach tensorboard to a particular run using the following command: This will produce a folder (`./save`) by default, where all the output is going to be stored including train/eval logs, tensorboard blobs, evaluation videos, and model snapshots. It is possible to attach tensorboard to a particular run using the following command: