Tuple Observations (#2)

* typo * change version to 0.1.0.dev0 * general requirements * version 0.1.1 * tuple obs wrapper * optimize tests with no resets * test tuple obs * must reset with wrappers * wrong gym id * format
minerl-wrappers · Jul 26, 2021 · 5ae7102 · 5ae7102
1 parent 6b96b2e
commit 5ae7102
Show file tree

Hide file tree

Showing 7 changed files with 120 additions and 83 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 # minerl-wrappers
 
-`minerl-wrapper` compiles common wrappers and standardizes code for reproducibility in the [MineRL environment](https://minerl.readthedocs.io/en/latest/index.html)!
+`minerl-wrappers` compiles common wrappers and standardizes code for reproducibility in the [MineRL environment](https://minerl.readthedocs.io/en/latest/index.html)!
 
 # Currently Supported Environments
 - MineRL Basic Environments
@@ -62,10 +62,17 @@ DEFAULT_CONFIG = {
         "randomize_action": False,
         "eval_epsilon": 0.001,
         "action_choices": None,
+        "include_vec_obs": False,
+        "tuple_obs_space": False,
     },
 }
 ```
 
+# Requirements
+- Java JDK 8
+- Python 3.7+
+- `minerl==0.4.0`
+
 # Install
 
 Make sure you have Java JDK 8 installed as the only Java version for MineRL.

diff --git a/minerl_wrappers/config.py b/minerl_wrappers/config.py
@@ -36,6 +36,8 @@
         "randomize_action": False,
         "eval_epsilon": 0.001,
         "action_choices": None,
+        "include_vec_obs": False,
+        "tuple_obs_space": False,
     },
 }
 

diff --git a/minerl_wrappers/pfrl_2020_wrappers.py b/minerl_wrappers/pfrl_2020_wrappers.py
@@ -33,6 +33,8 @@ def wrap_env(
     randomize_action,
     eval_epsilon,
     action_choices,
+    include_vec_obs=False,
+    tuple_obs_space=False,
 ):
     # wrap env: time limit...
     # Don't use `ContinuingTimeLimit` for testing, in order to avoid unexpected behavior on submissions.
@@ -59,7 +61,10 @@ def wrap_env(
         env = FrameSkip(env, skip=frame_skip)
     if gray_scale:
         env = GrayScaleWrapper(env, dict_space_key="pov")
-    env = ObtainPoVWrapper(env)
+    if not include_vec_obs:
+        env = ObtainPoVWrapper(env)
+    elif tuple_obs_space:
+        env = TupleObsWrapper(env)
     env = MoveAxisWrapper(
         env, source=-1, destination=0
     )  # convert hwc -> chw as Pytorch requires.
@@ -165,6 +170,17 @@ def observation(self, observation):
         return observation["pov"]
 
 
+class TupleObsWrapper(gym.ObservationWrapper):
+    def __init__(self, env):
+        super().__init__(env)
+        self.observation_space = gym.spaces.Tuple(
+            (self.observation_space["pov"], self.observation_space["vector"])
+        )
+
+    def observation(self, observation):
+        return observation["pov"], observation["vector"]
+
+
 class UnifiedObservationWrapper(gym.ObservationWrapper):
     """Take 'pov', 'compassAngle', 'inventory' and concatenate with scaling.
     Each element of 'inventory' is converted to a square whose side length is region_size.

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,7 +1,7 @@
 [tool.poetry]
 name = "minerl-wrappers"
-version = "0.1.0"
-description = "minerl-wrapper compiles common wrappers and standardizes code for reproducibility in the MineRL environment!"
+version = "0.1.1"
+description = "minerl-wrappers compiles common wrappers and standardizes code for reproducibility in the MineRL environment!"
 authors = ["Julius Frost"]
 
 [tool.poetry.dependencies]

diff --git a/tests/common.py b/tests/common.py
@@ -47,3 +47,17 @@ def build_and_run_step(gym_id, config_file=None, **kwargs):
     reset_and_sample_episode(env, 1)
     logging.debug("Closing MineRL environment...")
     env.close()
+
+
+def build_and_run_list_config(gym_id, list_config: list, max_steps=1):
+    env = gym.make(gym_id)
+    for config in list_config:
+        logging.debug(f"testing config: {config}")
+        wrapped_env = wrap(env, **config)
+        wrapped_env.reset()
+        for step in range(max_steps):
+            action = wrapped_env.action_space.sample()
+            _, _, done, _ = wrapped_env.step(action)
+            if done:
+                break
+    env.close()
diff --git a/tests/test_pfrl_2019_wrappers.py b/tests/test_pfrl_2019_wrappers.py
@@ -5,51 +5,43 @@
 import gym
 
 from minerl_wrappers import wrap
-from tests.common import reset_and_sample_episode
+from tests.common import build_and_run_list_config
 
 logging.basicConfig(level=logging.DEBUG)
 
 
 def test_pfrl_2019_wrappers():
-    env = gym.make("MineRLObtainDiamondDense-v0")
-    config_validation(env)
-    logging.debug("Testing default wrapper")
-    wrapped_env = wrap(env)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing frame_skip and frame_stack")
-    config = {
-        "pfrl_2019": True,
-        "pfrl_2019_config": {
-            "frame_skip": 4,
-            "frame_stack": 4,
+    gym_id = "MineRLObtainDiamondDense-v0"
+    config_validation(gym_id)
+    config_list = [
+        {},
+        {
+            "pfrl_2019": True,
+            "pfrl_2019_config": {
+                "frame_skip": 4,
+                "frame_stack": 4,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing gray_scale")
-    config = {
-        "pfrl_2019": True,
-        "pfrl_2019_config": {
-            "gray_scale": True,
+        {
+            "pfrl_2019": True,
+            "pfrl_2019_config": {
+                "gray_scale": True,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing random_action")
-    config = {
-        "pfrl_2019": True,
-        "pfrl_2019_config": {
-            "random_action": True,
-            "eval_epsilon": 1,
+        {
+            "pfrl_2019": True,
+            "pfrl_2019_config": {
+                "random_action": True,
+                "eval_epsilon": 1,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    env.close()
+    ]
+    build_and_run_list_config(gym_id, config_list, 4)
 
 
-def config_validation(env):
+def config_validation(gym_id):
     logging.debug("Config validation tests...")
+    env = gym.make(gym_id)
     config = {}
     wrap(env, **config)
     config = {
@@ -62,3 +54,4 @@ def config_validation(env):
         Path(__file__).absolute().parent.joinpath("./configs/pfrl_2019_basic.yaml")
     )
     wrap(env, config_file=config_file)
+    env.close()
diff --git a/tests/test_pfrl_2020_wrappers.py b/tests/test_pfrl_2020_wrappers.py
@@ -6,64 +6,68 @@
 
 from minerl_wrappers import wrap
 from minerl_wrappers.utils import load_means
-from tests.common import reset_and_sample_episode
+from tests.common import build_and_run_list_config
 
 logging.basicConfig(level=logging.DEBUG)
 
 
 def test_pfrl_2020_wrappers():
-    env = gym.make("MineRLObtainDiamondDenseVectorObf-v0")
-    config_validation(env)
+    gym_id = "MineRLObtainDiamondDenseVectorObf-v0"
+    config_validation(gym_id)
     means = load_means()
-    logging.debug("Testing default wrapper")
-    wrapped_env = wrap(env)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing preset action choices")
-    config = {
-        "pfrl_2020": True,
-        "pfrl_2020_config": {
-            "action_choices": means,
+    config_list = [
+        {},
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing frame_skip and frame_stack")
-    config = {
-        "pfrl_2020": True,
-        "pfrl_2020_config": {
-            "action_choices": means,
-            "frame_skip": 4,
-            "frame_stack": 4,
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+                "frame_skip": 4,
+                "frame_stack": 4,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing gray_scale")
-    config = {
-        "pfrl_2020": True,
-        "pfrl_2020_config": {
-            "action_choices": means,
-            "gray_scale": True,
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+                "gray_scale": True,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    logging.debug("Testing random_action")
-    config = {
-        "pfrl_2020": True,
-        "pfrl_2020_config": {
-            "action_choices": means,
-            "random_action": True,
-            "eval_epsilon": 1,
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+                "random_action": True,
+                "eval_epsilon": 1,
+            },
         },
-    }
-    wrapped_env = wrap(env, **config)
-    reset_and_sample_episode(wrapped_env, 4)
-    env.close()
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+                "include_vec_obs": True,
+            },
+        },
+        {
+            "pfrl_2020": True,
+            "pfrl_2020_config": {
+                "action_choices": means,
+                "include_vec_obs": True,
+                "tuple_obs_space": True,
+            },
+        },
+    ]
+    build_and_run_list_config(gym_id, config_list, 4)
 
 
-def config_validation(env):
+def config_validation(gym_id):
     logging.debug("Config validation tests...")
+    env = gym.make(gym_id)
     config = {}
     wrap(env, **config)
     config = {
@@ -85,3 +89,4 @@ def config_validation(env):
         Path(__file__).absolute().parent.joinpath("./configs/pfrl_2020_basic.yaml")
     )
     wrap(env, config_file=config_file)
+    env.close()