import numpy as np import torch from Hierarchical_Agents.HIRO import HIRO from Utilities.Data_Structures.Config import Config random.seed(1) np.random.seed(1) torch.manual_seed(1) config = Config() config.seed = 1 config.environment = gym.make("Pendulum-v0") config.num_episodes_to_run = 1500 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 = 1 config.use_GPU = False config.overwrite_existing_results_file = False config.randomise_random_seed = True config.save_model = False config.hyperparameters = { "LOWER_LEVEL": { "max_lower_level_timesteps": 3, "Actor": { "learning_rate": 0.001,
from Agents.Trainer import Trainer from Utilities.Data_Structures.Config import Config from Agents.DQN_Agents.DQN import DQN config = Config() config.seed = 1 config.environment = Four_Rooms_Environment( 15, 15, stochastic_actions_probability=0.25, random_start_user_place=True, random_goal_place=False) config.num_episodes_to_run = 1000 config.file_to_save_data_results = "Data_and_Graphs/Four_Rooms.pkl" config.file_to_save_results_graph = "Data_and_Graphs/Four_Rooms.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 = { "DQN_Agents": { "linear_hidden_units": [10, 5], "learning_rate": 0.01,
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,
from gym.wrappers import FlattenDictWrapper from Agents.DQN_Agents.DQN_HER import DQN_HER from Bit_Flipping_Environment import Bit_Flipping_Environment from Agents.Trainer import Trainer from Utilities.Data_Structures.Config import Config from Agents.DQN_Agents.DQN import DQN config = Config() config.seed = 1 config.environment = Bit_Flipping_Environment(14) config.num_episodes_to_run = 4500 config.file_to_save_data_results = None #"Data_and_Graphs/Bit_Flipping_Results_Data.pkl" config.file_to_save_results_graph = None #"Data_and_Graphs/Bit_Flipping_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 = { "DQN_Agents": { "learning_rate": 0.001, "batch_size": 128, "buffer_size": 100000, "epsilon_decay_rate_denominator": 150, "discount_rate": 0.999,