Esempi in Python per Config.num_episodes_to_run

Esempio n. 1

from Hierarchical_Agents.SNN_HRL import SNN_HRL
from TD3 import TD3
from Trainer import Trainer
from Utilities.Data_Structures.Config import Config
from Agents.DQN_Agents.DQN import DQN
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 = 2000
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": 64,
        "buffer_size": 40000,
        "epsilon": 0.1,
        "epsilon_decay_rate_denominator": 200,
        "discount_rate": 0.99,

Esempio n. 2

File: Test_HIRO.py Progetto: hyzcn/Deep-Reinforcement-Learning-Algorithms-with-PyTorch

import gym
import random
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,

Esempio n. 3

import gym

from Agents.Policy_Gradient_Agents.PPO import PPO
from Agents.Actor_Critic_Agents.DDPG import DDPG
from TD3 import TD3
from Agents.Trainer import Trainer
from Utilities.Data_Structures.Config import Config


config = Config()
config.seed = 1
config.environment = gym.make("MountainCarContinuous-v0")
config.num_episodes_to_run = 600
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 = {
    "Policy_Gradient_Agents": {
            "learning_rate": 0.05,
            "linear_hidden_units": [30, 15],
            "final_layer_activation": "TANH",