gr-libs 0.1.5__tar.gz → 0.1.7.post0__tar.gz

{gr_libs-0.1.5/gr_libs.egg-info → gr_libs-0.1.7.post0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gr_libs
-Version: 0.1.5
+Version: 0.1.7.post0
 Summary: Package with goal recognition frameworks baselines
 Author: Ben Nageris
 Author-email: Matan Shamir <matan.shamir@live.biu.ac.il>, Osher Elhadad <osher.elhadad@live.biu.ac.il>
@@ -17,6 +17,7 @@ Requires-Dist: torchvision
 Requires-Dist: rl_zoo3
 Requires-Dist: stable_baselines3[extra]
 Requires-Dist: sb3_contrib
+Requires-Dist: pytest
 Provides-Extra: minigrid
 Requires-Dist: gr_envs[minigrid]; extra == "minigrid"
 Provides-Extra: highway
@@ -111,6 +112,25 @@ After installing GRLib, you will have access to custom Gym environments, allowin
 
 Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tutorials`. These tutorials walk through the initialization and deployment process, showcasing how different GR algorithms adapt to emerging goals in various Gym environments.
 
+## Working with an initial dataset of trained agents
+gr_libs also includes a library of trained agents for the various supported environments within the package.
+To get the dataset of trained agents, you can run:
+```sh
+python download_dataset.py
+```
+
+An alternative is to use our docker image, which includes the dataset in it.
+You can:
+1. pull the image:
+```sh
+docker pull ghcr.io/MatanShamir1/gr_test_base:latest
+```
+2. run a container:
+```sh
+docker run -it ghcr.io/MatanShamir1/gr_test_base:latest bash
+```
+3. don't forget to install the package from within the container, go back to 'Setup' for that.
+
 ### Method 1: Writing a Custom Script
 
 1. **Create a recognizer**
@@ -118,6 +138,7 @@ Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tu
    Specify the domain name and specific environment for the recognizer, effectively telling it the domain theory - the collection of states and actions in the environment.
 
    ```python
+   import gr_libs.environment # Triggers gym env registration - you must run it!
    recognizer = Graql(
        domain_name="minigrid",
        env_name="MiniGrid-SimpleCrossingS13N4"

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/README.md

@@ -83,6 +83,25 @@ After installing GRLib, you will have access to custom Gym environments, allowin
 
 Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tutorials`. These tutorials walk through the initialization and deployment process, showcasing how different GR algorithms adapt to emerging goals in various Gym environments.
 
+## Working with an initial dataset of trained agents
+gr_libs also includes a library of trained agents for the various supported environments within the package.
+To get the dataset of trained agents, you can run:
+```sh
+python download_dataset.py
+```
+
+An alternative is to use our docker image, which includes the dataset in it.
+You can:
+1. pull the image:
+```sh
+docker pull ghcr.io/MatanShamir1/gr_test_base:latest
+```
+2. run a container:
+```sh
+docker run -it ghcr.io/MatanShamir1/gr_test_base:latest bash
+```
+3. don't forget to install the package from within the container, go back to 'Setup' for that.
+
 ### Method 1: Writing a Custom Script
 
 1. **Create a recognizer**
@@ -90,6 +109,7 @@ Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tu
    Specify the domain name and specific environment for the recognizer, effectively telling it the domain theory - the collection of states and actions in the environment.
 
    ```python
+   import gr_libs.environment # Triggers gym env registration - you must run it!
    recognizer = Graql(
        domain_name="minigrid",
        env_name="MiniGrid-SimpleCrossingS13N4"

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/__init__.py

@@ -1,2 +1,6 @@
 from gr_libs.recognizer.graml.graml_recognizer import ExpertBasedGraml, GCGraml
-from gr_libs.recognizer.gr_as_rl.gr_as_rl_recognizer import Graql
+from gr_libs.recognizer.gr_as_rl.gr_as_rl_recognizer import Graql
+try:
+    from ._version import version as __version__
+except ImportError:
+    __version__ = "0.0.0"  # fallback if file isn't present

gr_libs-0.1.7.post0/gr_libs/_version.py

@@ -0,0 +1,21 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = ["__version__", "__version_tuple__", "version", "version_tuple"]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+else:
+    VERSION_TUPLE = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+
+__version__ = version = '0.1.7.post0'
+__version_tuple__ = version_tuple = (0, 1, 7, 'post0')

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/environment/__init__.py

@@ -12,11 +12,11 @@ def is_extra_installed(package: str, extra: str) -> bool:
         return False  # The package is not installed
 
 # Check if `gr_libs[minigrid]` was installed
-for env in ["minigrid", "panda", "parking", "point_maze"]:
+for env in ["minigrid", "panda", "highway", "maze"]:
 	if is_extra_installed("gr_libs", f"gr_envs[{env}]"):
 		try:
 			importlib.import_module(f"gr_envs.{env}_scripts.envs")
 		except ImportError:
-			raise ImportError(f"gr_libs[{env}] was not installed, but gr_libs[{env}] requires it! if you messed with gr_libs installation, you can reinstall gr_libs.")
+			raise ImportError(f"gr_envs[{env}] was not installed, but gr_libs[{env}] requires it! if you messed with gr_envs installation, you can reinstall gr_libs.")
 	else:
 		warnings.warn(f"gr_libs[{env}] was not installed, skipping {env} imports.", RuntimeWarning)

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/environment/environment.py

@@ -105,7 +105,7 @@ class MinigridProperty(EnvProperty):
         env_id = problem_name.split("-DynamicGoal-")[0] + "-DynamicGoal-" + problem_name.split("-DynamicGoal-")[1]
         result = register(
             id=env_id,
-            entry_point="gr_libss.minigrid_scripts.envs:CustomColorEnv",
+            entry_point="gr_envs.minigrid_scripts.envs:CustomColorEnv",
             kwargs={"size": 13 if 'Simple' in problem_name else 9,
                     "num_crossings": 4 if 'Simple' in problem_name else 3,
                     "goal_pos": self.str_to_goal(problem_name),

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/metrics/metrics.py

@@ -5,7 +5,6 @@ import numpy as np
 
 from typing import Callable, Generator, List, Dict, Tuple, Any
 from math import log2
-from numpy.core.fromnumeric import mean
 from scipy.stats import wasserstein_distance
 from gymnasium.spaces.discrete import Discrete
 # import torch
@@ -43,7 +42,7 @@ def kl_divergence_norm_softmax(observations: List[Tuple[State, Any]], agent, act
         qp2_flatten_distribution_list: List[float] = agent.get_actions_probabilities(
             observation=(observation, agent_pos))
         distances.append(kl_divergence(qp1, qp2_flatten_distribution_list))
-    return mean(distances)
+    return np.mean(distances)
 
 
 def amplify(values, alpha=1.0):

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/ml/tabular/tabular_q_learner.py

@@ -351,7 +351,7 @@ class TabularQLearner(TabularRLAgent):
     def simplify_observation(self, observation):
         return [(obs['direction'], agent_pos_x, agent_pos_y, action) for ((obs, (agent_pos_x, agent_pos_y)), action) in observation] # list of tuples, each tuple the sample
         
-    def generate_observation(self, action_selection_method: MethodType, random_optimalism, save_fig = False, fig_path: str=None, env_prop=None):
+    def generate_observation(self, action_selection_method: MethodType, random_optimalism, save_fig=False, fig_path: str=None, env_prop=None):
         """
         Generate a single observation given a list of agents
 

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/ml/utils/storage.py

@@ -15,6 +15,13 @@ def get_storage_framework_dir(recognizer: str):
     return os.path.join(get_storage_dir(),recognizer)
 
 def get_storage_dir():
+    # Prefer local directory if it exists (e.g., in GitHub workspace)
+    if os.path.exists("dataset"):
+        return "dataset"
+    # Fall back to pre-mounted directory (e.g., in Docker container)
+    if os.path.exists("/preloaded_data"):
+        return "/preloaded_data"
+    # Default to "dataset" even if it doesn't exist (e.g., will be created)
     return "dataset"
 
 def _get_models_directory_name():

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/recognizer/graml/graml_recognizer.py

@@ -82,14 +82,14 @@ class Graml(LearningRecognizer):
 							dev_loader=DataLoader(dev_dataset, batch_size=self.env_prop.get_lstm_props().batch_size, shuffle=False, collate_fn=self.collate_func))
 			save_weights(model=self.model, path=self.model_file_path)
 
-	def goals_adaptation_phase(self, dynamic_goals: List[EnvProperty]):
+	def goals_adaptation_phase(self, dynamic_goals: List[EnvProperty], save_fig=False):
 		self.is_first_inf_since_new_goals = True
 		self.current_goals = dynamic_goals
 		# start by training each rl agent on the base goal set
 		self.embeddings_dict = {} # relevant if the embedding of the plan occurs during the goals adaptation phase
 		self.plans_dict = {} # relevant if the embedding of the plan occurs during the inference phase
 		for goal in self.current_goals:
-			obss = self.generate_sequences_library(goal)
+			obss = self.generate_sequences_library(goal, save_fig=save_fig)
 			self.plans_dict[str(goal)] = obss
 
 	def get_goal_plan(self, goal):
@@ -150,7 +150,7 @@ class Graml(LearningRecognizer):
 		return closest_goal
 	
 	@abstractmethod
-	def generate_sequences_library(self, goal: str) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
+	def generate_sequences_library(self, goal: str, save_fig=False) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
 		pass
 
 	# this function duplicates every sequence and creates a consecutive and non-consecutive version of it
@@ -192,10 +192,10 @@ class MCTSBasedGraml(BGGraml, GaAdaptingRecognizer):
 		super().__init__(*args, **kwargs)
 		if self.rl_agent_type==None: self.rl_agent_type = TabularQLearner
 
-	def generate_sequences_library(self, goal: str) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
+	def generate_sequences_library(self, goal: str, save_fig=False) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
 		problem_name = self.env_prop.goal_to_problem_str(goal)
 		img_path = os.path.join(get_policy_sequences_result_path(self.env_prop.domain_name, recognizer=self.__class__.__name__), problem_name + "_MCTS")
-		return mcts_model.plan(self.env_prop.name, problem_name, goal, save_fig=True, img_path=img_path, env_prop=self.env_prop)
+		return mcts_model.plan(self.env_prop.name, problem_name, goal, save_fig=save_fig, img_path=img_path, env_prop=self.env_prop)
 
 class ExpertBasedGraml(BGGraml, GaAgentTrainerRecognizer):
 	def __init__(self, *args, **kwargs):
@@ -206,15 +206,23 @@ class ExpertBasedGraml(BGGraml, GaAgentTrainerRecognizer):
 			else:
 				self.rl_agent_type = DeepRLAgent
 
-	def generate_sequences_library(self, goal: str) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
+	def generate_sequences_library(self, goal: str, save_fig=False) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
 		problem_name = self.env_prop.goal_to_problem_str(goal)
 		kwargs = {"domain_name":self.domain_name, "problem_name":problem_name}
 		if self.dynamic_train_configs_dict[problem_name][0] != None: kwargs["algorithm"] = self.dynamic_train_configs_dict[problem_name][0]
 		if self.dynamic_train_configs_dict[problem_name][1] != None: kwargs["num_timesteps"] = self.dynamic_train_configs_dict[problem_name][1]
 		agent = self.rl_agent_type(**kwargs)
 		agent.learn()
-		fig_path = get_and_create(f"{os.path.abspath(os.path.join(get_policy_sequences_result_path(domain_name=self.env_prop.domain_name, env_name=self.env_prop.name, recognizer=self.__class__.__name__), problem_name))}_bg_sequence")
-		return [agent.generate_observation(action_selection_method=metrics.greedy_selection, random_optimalism=False, save_fig=True, fig_path=fig_path, env_prop=self.env_prop)]
+		agent_kwargs = {
+			"action_selection_method": metrics.greedy_selection,
+			"random_optimalism": False,
+			"save_fig": save_fig,
+			"env_prop": self.env_prop
+		}
+		if save_fig:
+			fig_path = get_and_create(f"{os.path.abspath(os.path.join(get_policy_sequences_result_path(domain_name=self.env_prop.domain_name, env_name=self.env_prop.name, recognizer=self.__class__.__name__), problem_name))}_bg_sequence")
+			agent_kwargs["fig_path"] = fig_path
+		return [agent.generate_observation(**agent_kwargs)]
 
 	def goals_adaptation_phase(self, dynamic_goals: List[str], dynamic_train_configs):
 		self.dynamic_goals_problems = [self.env_prop.goal_to_problem_str(g) for g in dynamic_goals]
@@ -244,20 +252,21 @@ class GCGraml(Graml, GaAdaptingRecognizer):
 		gc_agent.learn()
 		self.agents.append(ContextualAgent(problem_name=self.env_prop.name, problem_goal="general", agent=gc_agent))
 
-	def generate_sequences_library(self, goal: str) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
+	def generate_sequences_library(self, goal: str, save_fig=False) -> List[List[Tuple[np.ndarray, np.ndarray]]]:
 		problem_name = self.env_prop.goal_to_problem_str(goal)
 		kwargs = {"domain_name":self.domain_name, "problem_name":self.env_prop.name} # problem name is env name in gc case
 		if self.original_train_configs[0][0] != None: kwargs["algorithm"] = self.original_train_configs[0][0]
 		if self.original_train_configs[0][1] != None: kwargs["num_timesteps"] = self.original_train_configs[0][1]
 		agent = self.rl_agent_type(**kwargs)
 		agent.learn()
-		fig_path = get_and_create(f"{os.path.abspath(os.path.join(get_policy_sequences_result_path(domain_name=self.env_prop.domain_name, env_name=self.env_prop.name, recognizer=self.__class__.__name__), problem_name))}_gc_sequence")
 		agent_kwargs = {
 			"action_selection_method": metrics.stochastic_amplified_selection,
 			"random_optimalism": True,
-			"save_fig": True,
-			"fig_path": fig_path
+			"save_fig": save_fig
 		}
+		if save_fig:
+			fig_path = get_and_create(f"{os.path.abspath(os.path.join(get_policy_sequences_result_path(domain_name=self.env_prop.domain_name, env_name=self.env_prop.name, recognizer=self.__class__.__name__), problem_name))}_gc_sequence")
+			agent_kwargs["fig_path"] = fig_path
 		if self.env_prop.use_goal_directed_problem(): agent_kwargs["goal_directed_problem"] = problem_name
 		else: agent_kwargs["goal_directed_goal"] = goal
 		obss = []

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs/recognizer/recognizer.py

@@ -1,6 +1,5 @@
 from abc import ABC, abstractmethod
 from typing import List, Type
-
 from gr_libs.environment.environment import EnvProperty, SUPPORTED_DOMAINS
 from gr_libs.environment.utils.utils import domain_to_env_property
 from gr_libs.ml.base.rl_agent import RLAgent

{gr_libs-0.1.5 → gr_libs-0.1.7.post0/gr_libs.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gr_libs
-Version: 0.1.5
+Version: 0.1.7.post0
 Summary: Package with goal recognition frameworks baselines
 Author: Ben Nageris
 Author-email: Matan Shamir <matan.shamir@live.biu.ac.il>, Osher Elhadad <osher.elhadad@live.biu.ac.il>
@@ -17,6 +17,7 @@ Requires-Dist: torchvision
 Requires-Dist: rl_zoo3
 Requires-Dist: stable_baselines3[extra]
 Requires-Dist: sb3_contrib
+Requires-Dist: pytest
 Provides-Extra: minigrid
 Requires-Dist: gr_envs[minigrid]; extra == "minigrid"
 Provides-Extra: highway
@@ -111,6 +112,25 @@ After installing GRLib, you will have access to custom Gym environments, allowin
 
 Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tutorials`. These tutorials walk through the initialization and deployment process, showcasing how different GR algorithms adapt to emerging goals in various Gym environments.
 
+## Working with an initial dataset of trained agents
+gr_libs also includes a library of trained agents for the various supported environments within the package.
+To get the dataset of trained agents, you can run:
+```sh
+python download_dataset.py
+```
+
+An alternative is to use our docker image, which includes the dataset in it.
+You can:
+1. pull the image:
+```sh
+docker pull ghcr.io/MatanShamir1/gr_test_base:latest
+```
+2. run a container:
+```sh
+docker run -it ghcr.io/MatanShamir1/gr_test_base:latest bash
+```
+3. don't forget to install the package from within the container, go back to 'Setup' for that.
+
 ### Method 1: Writing a Custom Script
 
 1. **Create a recognizer**
@@ -118,6 +138,7 @@ Tutorials demonstrating basic ODGR scenarios is available in the sub-package `tu
    Specify the domain name and specific environment for the recognizer, effectively telling it the domain theory - the collection of states and actions in the environment.
 
    ```python
+   import gr_libs.environment # Triggers gym env registration - you must run it!
    recognizer = Graql(
        domain_name="minigrid",
        env_name="MiniGrid-SimpleCrossingS13N4"

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs.egg-info/SOURCES.txt

@@ -1,10 +1,5 @@
-.gitignore
 README.md
-all_experiments.py
-consts.py
-odgr_executor.py
 pyproject.toml
-.github/workflows/release.yml
 evaluation/analyze_results_cross_alg_cross_domain.py
 evaluation/create_minigrid_map_image.py
 evaluation/file_system.py
@@ -15,6 +10,7 @@ evaluation/generate_task_specific_statistics_plots.py
 evaluation/get_plans_images.py
 evaluation/increasing_and_decreasing_.py
 gr_libs/__init__.py
+gr_libs/_version.py
 gr_libs.egg-info/PKG-INFO
 gr_libs.egg-info/SOURCES.txt
 gr_libs.egg-info/dependency_links.txt
@@ -54,9 +50,10 @@ gr_libs/ml/utils/format.py
 gr_libs/ml/utils/math.py
 gr_libs/ml/utils/other.py
 gr_libs/ml/utils/storage.py
+gr_libs/problems/__init__.py
+gr_libs/problems/consts.py
 gr_libs/recognizer/__init__.py
 gr_libs/recognizer/recognizer.py
-gr_libs/recognizer/recognizer_doc.md
 gr_libs/recognizer/gr_as_rl/__init__.py
 gr_libs/recognizer/gr_as_rl/gr_as_rl_recognizer.py
 gr_libs/recognizer/graml/__init__.py
@@ -64,6 +61,8 @@ gr_libs/recognizer/graml/gr_dataset.py
 gr_libs/recognizer/graml/graml_recognizer.py
 gr_libs/recognizer/utils/__init__.py
 gr_libs/recognizer/utils/format.py
+tests/test_graml.py
+tests/test_graql.py
 tutorials/graml_minigrid_tutorial.py
 tutorials/graml_panda_tutorial.py
 tutorials/graml_parking_tutorial.py

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs.egg-info/requires.txt

@@ -6,6 +6,7 @@ torchvision
 rl_zoo3
 stable_baselines3[extra]
 sb3_contrib
+pytest
 
 [highway]
 gr_envs[highway]

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/gr_libs.egg-info/top_level.txt

@@ -1,4 +1,7 @@
+CI
+build
 dist
 evaluation
 gr_libs
+tests
 tutorials

{gr_libs-0.1.5 → gr_libs-0.1.7.post0}/pyproject.toml

@@ -22,7 +22,8 @@ dependencies = [
     "torchvision",
     "rl_zoo3",
     "stable_baselines3[extra]",
-    "sb3_contrib"
+    "sb3_contrib",
+    "pytest"
 ]
 classifiers = [
     "Programming Language :: Python :: 3",
@@ -42,3 +43,4 @@ packages = {find = {}}
 [tool.setuptools_scm]
 version_scheme = "post-release"
 local_scheme = "node-and-date"
+write_to = "gr_libs/_version.py"  # This line writes the version to a file within the package

gr_libs-0.1.7.post0/tests/test_graml.py

@@ -0,0 +1,16 @@
+from tutorials.graml_minigrid_tutorial import run_graml_minigrid_tutorial
+from tutorials.graml_panda_tutorial import run_graml_panda_tutorial
+from tutorials.graml_parking_tutorial import run_graml_parking_tutorial
+from tutorials.graml_point_maze_tutorial import run_graml_point_maze_tutorial
+
+def test_graml_minigrid_tutorial():
+	run_graml_minigrid_tutorial()
+
+def test_graml_panda_tutorial():
+	run_graml_panda_tutorial()
+
+def test_graml_parking_tutorial():
+	run_graml_parking_tutorial()
+
+def test_graml_point_maze_tutorial():
+	run_graml_point_maze_tutorial()

gr_libs-0.1.7.post0/tests/test_graql.py

@@ -0,0 +1,4 @@
+from tutorials.graql_minigrid_tutorial import run_graql_minigrid_tutorial
+
+def test_graql_minigrid_tutorial():
+	run_graql_minigrid_tutorial()

gr_libs-0.1.7.post0/tutorials/graml_minigrid_tutorial.py

@@ -0,0 +1,34 @@
+from gr_libs.environment.environment import MINIGRID, QLEARNING
+from gr_libs.metrics.metrics import stochastic_amplified_selection
+from gr_libs.ml.tabular.tabular_q_learner import TabularQLearner
+from gr_libs.ml.utils.format import random_subset_with_order
+from gr_libs import ExpertBasedGraml
+
+def run_graml_minigrid_tutorial():
+    recognizer = ExpertBasedGraml(
+        domain_name=MINIGRID,
+        env_name="MiniGrid-SimpleCrossingS13N4"
+    )
+
+    recognizer.domain_learning_phase(base_goals=[(11,1), (11,11), (1,11), (7,11), (8,1), (10,6), (6,9), (11,3), (11,5)],
+                                    train_configs=[(QLEARNING, 100000) for _ in range(9)])
+
+    recognizer.goals_adaptation_phase(
+        dynamic_goals = [(11,1), (11,11), (1,11)],
+        dynamic_train_configs=[(QLEARNING, 100000) for _ in range(3)] # for expert sequence generation.
+    )
+    # TD3 is different from recognizer and expert algorithms, which are SAC #
+    actor = TabularQLearner(domain_name="minigrid", problem_name="MiniGrid-SimpleCrossingS13N4-DynamicGoal-11x1-v0", algorithm=QLEARNING, num_timesteps=100000)
+    actor.learn()
+    # sample is generated stochastically to simulate suboptimal behavior, noise is added to the actions values #
+    full_sequence = actor.generate_observation(
+        action_selection_method=stochastic_amplified_selection,
+        random_optimalism=True, # the noise that's added to the actions
+    )
+
+    partial_sequence = random_subset_with_order(full_sequence, (int)(0.5 * len(full_sequence)), is_consecutive=False)
+    closest_goal = recognizer.inference_phase(partial_sequence, (11,1), 0.5)
+    print(f"closest_goal returned by GRAML: {closest_goal}\nactual goal actor aimed towards: (11, 1)")
+
+if __name__ == "__main__":
+    run_graml_minigrid_tutorial()

gr_libs-0.1.7.post0/tutorials/graml_panda_tutorial.py

@@ -0,0 +1,41 @@
+
+import numpy as np
+from stable_baselines3 import PPO, SAC
+import gr_libs.environment.environment
+from gr_libs.environment.environment import PANDA, EnvProperty, GCEnvProperty, PandaProperty
+from gr_libs.environment.utils.utils import domain_to_env_property
+from gr_libs.metrics.metrics import stochastic_amplified_selection
+from gr_libs.ml.neural.deep_rl_learner import DeepRLAgent, GCDeepRLAgent
+from gr_libs.ml.utils.format import random_subset_with_order
+from gr_libs import GCGraml
+
+def run_graml_panda_tutorial():
+    recognizer = GCGraml( # TODO make these tutorials into pytests
+        domain_name=PANDA,
+        env_name="PandaMyReachDense"
+    )
+    recognizer.domain_learning_phase(
+        base_goals=[np.array([PandaProperty.sample_goal()]) for _ in range(1,30)],
+        train_configs=[(SAC, 800000)]
+    )
+    recognizer.goals_adaptation_phase(
+        dynamic_goals=[np.array([[-0.1, -0.1, 0.1]]), np.array([[-0.1, 0.1, 0.1]]), np.array([[0.2, 0.2, 0.1]])]
+    )
+    # TD3 is different from recognizer and expert algorithms, which are SAC #
+    property_type = domain_to_env_property(PANDA)
+    env_property = property_type("PandaMyReachDense")
+    problem_name = env_property.goal_to_problem_str(np.array([[-0.1, -0.1, 0.1]]))
+    actor = DeepRLAgent(domain_name=PANDA, problem_name=problem_name, algorithm=PPO, num_timesteps=400000)
+    actor.learn()
+    # sample is generated stochastically to simulate suboptimal behavior, noise is added to the actions values #
+    full_sequence = actor.generate_observation(
+        action_selection_method=stochastic_amplified_selection,
+        random_optimalism=True, # the noise that's added to the actions
+    )
+
+    partial_sequence = random_subset_with_order(full_sequence, (int)(0.5 * len(full_sequence)), is_consecutive=False)
+    closest_goal = recognizer.inference_phase(partial_sequence, np.array([[-0.1, -0.1, 0.1]]), 0.5)
+    print(f"closest_goal returned by GRAML: {closest_goal}\nactual goal actor aimed towards: [-0.1, -0.1, 0.1]")
+
+if __name__ == "__main__":
+    run_graml_panda_tutorial()

gr_libs-0.1.7.post0/tutorials/graml_parking_tutorial.py

@@ -0,0 +1,39 @@
+
+from stable_baselines3 import PPO, SAC, TD3
+from gr_libs.environment.environment import PARKING, EnvProperty, GCEnvProperty, ParkingProperty
+from gr_libs.metrics.metrics import stochastic_amplified_selection
+from gr_libs.ml.neural.deep_rl_learner import DeepRLAgent, GCDeepRLAgent
+from gr_libs.ml.utils.format import random_subset_with_order
+from gr_libs.recognizer.graml.graml_recognizer import ExpertBasedGraml, GCGraml
+import gr_libs.environment.environment
+
+def run_graml_parking_tutorial():
+    recognizer = GCGraml(
+        domain_name=PARKING,
+        env_name="Parking-S-14-PC-"
+    )
+                        
+    recognizer.domain_learning_phase(
+        [i for i in range(1,21)],
+        [(PPO, 200000)]
+    )
+    recognizer.goals_adaptation_phase(
+        dynamic_goals = ["1", "11", "21"]
+        # no need for expert sequence generation since GCRL is used
+    )
+
+    # TD3 is different from recognizer and expert algorithms, which are SAC #
+    actor = DeepRLAgent(domain_name="parking", problem_name="Parking-S-14-PC--GI-11-v0", algorithm=TD3, num_timesteps=400000)
+    actor.learn()
+    # sample is generated stochastically to simulate suboptimal behavior, noise is added to the actions values #
+    full_sequence = actor.generate_observation(
+        action_selection_method=stochastic_amplified_selection,
+        random_optimalism=True, # the noise that's added to the actions
+    )
+
+    partial_sequence = random_subset_with_order(full_sequence, (int)(0.5 * len(full_sequence)), is_consecutive=False)
+    closest_goal = recognizer.inference_phase(partial_sequence, ParkingProperty("Parking-S-14-PC--GI-11-v0").str_to_goal(), 0.5)
+    print(f"closest_goal returned by GRAML: {closest_goal}\nactual goal actor aimed towards: 11")
+
+if __name__ == "__main__":
+    run_graml_parking_tutorial()

gr_libs-0.1.7.post0/tutorials/graml_point_maze_tutorial.py

@@ -0,0 +1,39 @@
+
+from stable_baselines3 import SAC, TD3
+from gr_libs.environment.environment import POINT_MAZE, PointMazeProperty
+from gr_libs.metrics.metrics import stochastic_amplified_selection
+from gr_libs.ml.neural.deep_rl_learner import DeepRLAgent
+from gr_libs.ml.utils.format import random_subset_with_order
+from gr_libs.recognizer.graml.graml_recognizer import ExpertBasedGraml
+
+def run_graml_point_maze_tutorial():
+    recognizer = ExpertBasedGraml(
+        domain_name=POINT_MAZE,
+        env_name="PointMaze-FourRoomsEnvDense-11x11"
+    )
+
+    recognizer.domain_learning_phase(
+        [(9,1), (9,9), (1,9), (3,3), (3,4), (8,2), (3,7), (2,8)],
+        [(SAC, 200000) for _ in range(8)]
+    )
+
+    recognizer.goals_adaptation_phase(
+        dynamic_goals = [(4,4), (7,3), (3,7)],
+        dynamic_train_configs=[(SAC, 200000) for _ in range(3)] # for expert sequence generation.
+    )
+
+    # TD3 is different from recognizer and expert algorithms, which are SAC #
+    actor = DeepRLAgent(domain_name="point_maze", problem_name="PointMaze-FourRoomsEnvDense-11x11-Goal-4x4", algorithm=TD3, num_timesteps=200000)
+    actor.learn()
+    # sample is generated stochastically to simulate suboptimal behavior, noise is added to the actions values #
+    full_sequence = actor.generate_observation(
+        action_selection_method=stochastic_amplified_selection,
+        random_optimalism=True, # the noise that's added to the actions
+    )
+
+    partial_sequence = random_subset_with_order(full_sequence, (int)(0.5 * len(full_sequence)))
+    closest_goal = recognizer.inference_phase(partial_sequence, PointMazeProperty("PointMaze-FourRoomsEnvDense-11x11-Goal-4x4").str_to_goal(), 0.5)
+    print(f"closest_goal returned by GRAML: {closest_goal}\nactual goal actor aimed towards: (4, 4)")
+
+if __name__ == "__main__":
+    run_graml_point_maze_tutorial()

gr_libs-0.1.7.post0/tutorials/graql_minigrid_tutorial.py

@@ -0,0 +1,34 @@
+from gr_libs.environment.environment import QLEARNING
+from gr_libs.metrics.metrics import stochastic_amplified_selection
+from gr_libs.ml.tabular.tabular_q_learner import TabularQLearner
+from gr_libs.ml.utils.format import random_subset_with_order
+from gr_libs import Graql
+
+def run_graql_minigrid_tutorial():
+    recognizer = Graql(
+        domain_name="minigrid",
+        env_name="MiniGrid-SimpleCrossingS13N4"
+    )
+
+    #Graql doesn't have a domain learning phase, so we skip it
+
+    recognizer.goals_adaptation_phase(
+        dynamic_goals = [(11,1), (11,11), (1,11)],
+        dynamic_train_configs=[(QLEARNING, 100000) for _ in range(3)] # for expert sequence generation.
+    )
+    # TD3 is different from recognizer and expert algorithms, which are SAC #
+    actor = TabularQLearner(domain_name="minigrid", problem_name="MiniGrid-SimpleCrossingS13N4-DynamicGoal-11x1-v0", algorithm=QLEARNING, num_timesteps=100000)
+    actor.learn()
+    # sample is generated stochastically to simulate suboptimal behavior, noise is added to the actions values #
+    full_sequence = actor.generate_observation(
+        action_selection_method=stochastic_amplified_selection,
+        random_optimalism=True, # the noise that's added to the actions
+    )
+
+    partial_sequence = random_subset_with_order(full_sequence, (int)(0.5 * len(full_sequence)), is_consecutive=False)
+    closest_goal = recognizer.inference_phase(partial_sequence, (11,1), 0.5)
+    print(f"closest_goal returned by Graql: {closest_goal}\nactual goal actor aimed towards: (11, 1)")
+    return closest_goal, (11,1)
+
+if __name__ == "__main__":
+    run_graql_minigrid_tutorial()

gr_libs-0.1.5/.github/workflows/release.yml

@@ -1,32 +0,0 @@
-name: Publish to PyPI
-
-on:
-  push:
-    tags:
-      - "v*"
-
-jobs:
-  build-and-publish:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Check out the repository
-        uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.11"
-
-      - name: Install build dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install build twine
-
-      - name: Build the package
-        run: python -m build  # Uses pyproject.toml instead of setup.py
-
-      - name: Publish to PyPI
-        env:
-          PYPY_API_TOKEN: ${{ secrets.PYPI_API_TOKEN }}
-        run: python -m twine upload dist/* -u __token__ -p $PYPY_API_TOKEN