Merge pull request #94 from Unity-Technologies/fix-21

Hotfix release - v2.1
Unity-Technologies · May 21, 2019 · f121d5a · f121d5a
2 parents d31de13 + c73276e
commit f121d5a
Show file tree

Hide file tree

Showing 5 changed files with 34 additions and 30 deletions.
diff --git a/README.md b/README.md
@@ -34,6 +34,9 @@ To learn more, please read our AAAI Workshop paper:
    * Additional visual themes, obstacles, enemy types, and floor difficulties added.
    * Additional reset parameters added to customize generated towers. Go [here](./reset-parameters.md) for details on the parameters and their values.
    * Various bugs fixed and performance improvements.
+* v2.1 Hotfix release.
+   * Resolves issue with new seeds not being applied on `env.reset`.
+   * Resolves issue with underspecified observation space.
 
 
 ## Installation
@@ -53,11 +56,11 @@ Python dependencies (also in [setup.py](https://github.com/Unity-Technologies/ob
 
 | *Platform*     | *Download Link*                                                                     |
 | --- | --- |
-| Linux (x86_64) | https://storage.googleapis.com/obstacle-tower-build/v2.0/obstacletower_v2.0_linux.zip   |
-| Mac OS X       | https://storage.googleapis.com/obstacle-tower-build/v2.0/obstacletower_v2.0_osx.zip     |
-| Windows        | https://storage.googleapis.com/obstacle-tower-build/v2.0/obstacletower_v2.0_windows.zip |
+| Linux (x86_64) | https://storage.googleapis.com/obstacle-tower-build/v2.1/obstacletower_v2.1_linux.zip   |
+| Mac OS X       | https://storage.googleapis.com/obstacle-tower-build/v2.1/obstacletower_v2.1_osx.zip     |
+| Windows        | https://storage.googleapis.com/obstacle-tower-build/v2.1/obstacletower_v2.1_windows.zip |
 
-For checksums on these files, see [here](https://storage.googleapis.com/obstacle-tower-build/v1.3/ote-v1.3-checksums.txt).
+For checksums on these files, see [here](https://storage.googleapis.com/obstacle-tower-build/v2.1/ote-v2.1-checksums.txt).
 
 ### Install the Gym interface
 

diff --git a/examples/basic_usage.ipynb b/examples/basic_usage.ipynb
diff --git a/examples/gcp_training.md b/examples/gcp_training.md
@@ -107,8 +107,8 @@ cd ../
 This page lists the URLs for downloading Obstacle Tower for various platforms. [https://github.com/Unity-Technologies/obstacle-tower-env](https://github.com/Unity-Technologies/obstacle-tower-env). For GCP, run
 
 ```bash
-wget https://storage.googleapis.com/obstacle-tower-build/v2.0/obstacletower_v2.0_linux.zip
-unzip obstacletower_v2.0_linux.zip
+wget https://storage.googleapis.com/obstacle-tower-build/v2.1/obstacletower_v2.1_linux.zip
+unzip obstacletower_v2.1_linux.zip
 ```
 
 ### Install Dopamine
@@ -157,7 +157,7 @@ cp dopamine_otc/unity_lib.py dopamine/dopamine/discrete_domains/unity_lib.py
 cp dopamine_otc/rainbow_otc.gin dopamine/dopamine/agents/rainbow/configs/rainbow_otc.gin
 ```
 
-If you didn’t extract the `obstacletower_v2.0_linux.zip` to the home directory, you will need to edit `rainbow_otc.gin`, specifically `create_otc_environment.environment_path` should correspond to the path to your extracted OTC executable file. 
+If you didn’t extract the `obstacletower_v2.1_linux.zip` to the home directory, you will need to edit `rainbow_otc.gin`, specifically `create_otc_environment.environment_path` should correspond to the path to your extracted OTC executable file. 
 
 Furthermore, within this file you will find settings on how long to train for, and how often to evaluate your agent. Each iteration, Dopamine will train for `Runner.training_steps`, evaluate (i.e. run in inference mode) for `Runner.evaluation_steps`, record these results, and checkpoint the agent. It will repeat this process `Runner.num_iterations` number of times before quitting. For instance, you can change `Runner.num_iterations` to 40 to train for 10 million steps. You can also reduce `Runner.evaluation_steps` to reduce the time spent not training. There are other hyperparameters found in this file, which you can modify to improve performance. But for the sake of this exercise, you may leave them as-is. 
 

diff --git a/obstacle_tower_env.py b/obstacle_tower_env.py
@@ -20,7 +20,7 @@ class UnityGymException(error.Error):
 
 
 class ObstacleTowerEnv(gym.Env):
-    ALLOWED_VERSIONS = ['2.0']
+    ALLOWED_VERSIONS = ['2.0', '2.1']
 
     def __init__(self, environment_filename=None, docker_training=False, worker_id=0, retro=True,
                  timeout_wait=30, realtime_mode=False, config=None, greyscale=False):
@@ -140,8 +140,9 @@ def __init__(self, environment_filename=None, docker_training=False, worker_id=0
             max_float = np.finfo(np.float32).max
             keys_space = spaces.Discrete(5)
             time_remaining_space = spaces.Box(low=0.0, high=max_float, shape=(1,), dtype=np.float32)
+            floor_space = spaces.Discrete(9999)
             self._observation_space = spaces.Tuple(
-                (image_space, keys_space, time_remaining_space)
+                (image_space, keys_space, time_remaining_space, floor_space)
             )
 
     def done_grading(self):

diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name='obstacle_tower_env',
-    version='2.0',
+    version='2.1',
     author='Unity Technologies',
     url='https://github.com/Unity-Technologies/obstacle-tower-env',
     py_modules=["obstacle_tower_env"],