v1.0 documentation

README.md

@@ -144,7 +144,7 @@ v0.6.1)
 
 ## TODO
 
-- [ ] Add custom resolutions
+- [x] Add custom resolutions
 - [x] Add inference viewer to the environment
 - [x] Offer a gym wrapper for training
 - [x] Improve the way the agent spawns
@@ -155,7 +155,10 @@ v0.6.1)
 ## Version History
 
 - v1.0
+    - Adds custom resolution to both Unity and Gym environments
     - Adds inference mode to the environment to visualize trained agents
+    - Prizes announced
+    - More details about the competition
 
 - v0.6.1 (Environment only) 
     - Fix rare events of agent falling through the floor or objects flying in the air when resetting an arena

documentation/training.md

@@ -46,7 +46,9 @@ env= UnityEnvironment(
         docker_training=False,      # Whether or not you are training inside a docker
         no_graphics=False,          # Always set to False
         n_arenas=4,                 # Number of arenas in your environment
-        play=False                  # Set to False for training                
+        play=False,                 # Set to False for training
+        inference=False,            # Set to true to watch your agent in action
+        resolution=None             # Int: resolution of the agent's square camera (in [4,512], default 84)
     )
 ```
 

examples/visualizeLightsOff.py

@@ -16,7 +16,7 @@ run_seed = 1
 docker_target_name = None
 no_graphics = False
 n_arenas = 4
-resolution = 32
+resolution = 128
 
 if env_path is not None:
     env_path = (env_path.strip()