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,
"linear_hidden_units": [20, 20],
"final_layer_activation": "TANH",
"batch_norm": False,
"tau": 0.005,
"gradient_clipping_norm": 5
},
"Critic": {
"learning_rate": 0.01,
import numpy as np
import torch
random.seed(1)
np.random.seed(1)
torch.manual_seed(1)
config = Config()
config.seed = 1
config.environment = Bit_Flipping_Environment(4)
config.num_episodes_to_run = 1
config.file_to_save_data_results = None
config.file_to_save_results_graph = None
config.visualise_individual_results = False
config.visualise_overall_agent_results = False
config.randomise_random_seed = False
config.runs_per_agent = 1
config.use_GPU = False
config.hyperparameters = {
"DQN_Agents": {
"learning_rate": 0.005,
"batch_size": 3,
"buffer_size": 40000,
"epsilon": 0.1,
"epsilon_decay_rate_denominator": 200,
"discount_rate": 0.99,
"tau": 0.1,
"alpha_prioritised_replay": 0.6,
"beta_prioritised_replay": 0.4,