update README and config

examples/sweep/wandb/readme.md

@@ -4,8 +4,21 @@ You can improve the performance of your RL agents with hyperparameter tuning. It
 
 ## Prerequisites
 
-Ensure you have Weights & Biases: `pip install wandb` installed on top of benchmarl requirements.
+- Ensure you have Weights & Biases: `pip install wandb` installed on top of benchmarl requirements.
 
+- Update the `benchmarl/conf/config.yaml` with your desired experiment setup, e.g.:
+
+```yaml
+defaults:
+  - experiment: base_experiment
+  - algorithm: ippo
+  - task: customenv/task_1
+  - model: layers/mlp
+  - model@critic_model: layers/mlp
+  - _self_
+
+seed: 0
+```
 
 ## Step 1: Define Your Sweep Configuration
 

examples/sweep/wandb/sweepconfig.yaml

@@ -1,23 +1,5 @@
-'''
-Read this blog post for more details
-https://wandb.ai/adrishd/hydra-example/reports/Configuring-W-B-Projects-with-Hydra--VmlldzoxNTA2MzQw?galleryTag=posts&utm_source=fully_connected&utm_medium=blog&utm_campaign=hydra
-
-Also you need to change the config.yaml like following: 
-
-# defaults:
-#   - experiment: base_experiment
-#   - algorithm: ippo
-#   - task: customenv/task_1
-#   - model: layers/mlp
-#   - model@critic_model: layers/mlp
-#   - _self_
-
-# seed: 0
-
-'''
-
 program: PATH_TO_YOUR_DIRECTORY\benchmarl\run.py
-project: "sweep_benchmarl"
+project: "YOUR_PROJECT_NAME"
 entity: "YOUR_ENTITY_NAME"
 
 method: bayes 
@@ -57,7 +39,6 @@ parameters:
     # distribution: categorical
 
 
-
 early_terminate:
   type: hyperband
   max_iter: 27