readme and installation

README.md

@@ -1,5 +1,13 @@
 # CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
 
+## Installation 
+
+All of the dependencies are in the `conda_env.yml` file. They can be installed manually or with the following command:
+
+```
+conda env create -f conda_env.yml
+```
+
 ## Instructions
 To train a CURL agent on the `cartpole swingup` task from image-based observations run `bash script/run.sh` from the root of this directory. The `run.sh` file contains the following command, which you can modify to try different environments / hyperparamters.
 ```

conda_env.yml

@@ -8,10 +8,13 @@ dependencies:
   - cudatoolkit=9.2
   - absl-py
   - pyparsing
+  - pillow=6.1
   - pip:
     - termcolor
     - git+git://github.com/deepmind/dm_control.git
     - git+git://github.com/1nadequacy/dmc2gym.git
     - tb-nightly
     - imageio
-    - imageio-ffmpeg
+    - imageio-ffmpeg
+    - torchvision
+    - scikit-image

utils.py

@@ -6,7 +6,6 @@ import os
 from collections import deque
 import random
 from torch.utils.data import Dataset, DataLoader
-from torchvision import transforms
 import time
 from skimage.util.shape import view_as_windows