from Hierarchical_Agents.SNN_HRL import SNN_HRL
from Agents.Trainer import Trainer
from Utilities.Data_Structures.Config import Config
from Agents.DQN_Agents.DQN import DQN
from Agents.Hierarchical_Agents.h_DQN import h_DQN
from Environments.Long_Corridor_Environment import Long_Corridor_Environment

config = Config()
config.seed = 1
config.env_parameters = {"stochasticity_of_action_right": 0.5}
config.environment = Long_Corridor_Environment(
    stochasticity_of_action_right=config.
    env_parameters["stochasticity_of_action_right"])
config.num_episodes_to_run = 10000
config.file_to_save_data_results = "Data_and_Graphs/Long_Corridor_Results_Data.pkl"
config.file_to_save_results_graph = "Data_and_Graphs/Long_Corridor_Results_Graph.png"
config.show_solution_score = False
config.visualise_individual_results = False
config.visualise_overall_agent_results = True
config.standard_deviation_results = 1.0
config.runs_per_agent = 3
config.use_GPU = False
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.save_model = False

config.hyperparameters = {
    "h_DQN": {
        "CONTROLLER": {
            "batch_size":
            256,
import gym

from Hierarchical_Agents.SNN_HRL import SNN_HRL
from Agents.Trainer import Trainer
from Utilities.Data_Structures.Config import Config
from Agents.DQN_Agents.DQN import DQN
from Agents.Hierarchical_Agents.h_DQN import h_DQN

config = Config()
config.seed = 1
config.environment = gym.make("Taxi-v2")
config.env_parameters = {}
config.num_episodes_to_run = 10000
config.file_to_save_data_results = None
config.file_to_save_results_graph = None
config.show_solution_score = False
config.visualise_individual_results = False
config.visualise_overall_agent_results = True
config.standard_deviation_results = 1.0
config.runs_per_agent = 3
config.use_GPU = False
config.overwrite_existing_results_file = False
config.randomise_random_seed = True
config.save_model = False

config.hyperparameters = {
    "h_DQN": {
        "CONTROLLER": {
            "batch_size":
            256,
            "learning_rate":