import gym
from agents.hierarchical_agents.HRL.HRL import HRL
from agents.Trainer import Trainer
from utilities.data_structures.Config import Config
config = Config()
config.environment = gym.make("Taxi-v2")
config.seed = 1
config.env_parameters = {}
config.num_episodes_to_run = 2000
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
linear_hidden_units = [32, 32]
learning_rate = 0.01
buffer_size = 100000
batch_size = 256
batch_norm = False
embedding_dimensionality = 10
gradient_clipping_norm = 5
update_every_n_steps = 1
from agents.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.load_model = False
config.hyperparameters = {
"h_DQN": {
"CONTROLLER": {
"batch_size":
