394 lines
17 KiB
Python
394 lines
17 KiB
Python
import os
|
|
import pickle
|
|
from copy import deepcopy
|
|
import numpy as np
|
|
import pandas as pd
|
|
import torch
|
|
import torch.nn as nn
|
|
from environment import ESSEnv
|
|
from tools import get_episode_return, test_one_episode, optimization_base_result
|
|
|
|
os.environ['KMP_DUPLICATE_LIB_OK'] = 'TRUE'
|
|
|
|
|
|
class ActorPPO(nn.Module):
|
|
def __init__(self, mid_dim, state_dim, action_dim, layer_norm=False):
|
|
super().__init__()
|
|
self.layer_norm = layer_norm
|
|
self.net = nn.Sequential(
|
|
nn.Linear(state_dim, mid_dim), nn.ReLU(),
|
|
nn.Linear(mid_dim, mid_dim), nn.ReLU(),
|
|
nn.Linear(mid_dim, mid_dim), nn.Hardswish(),
|
|
nn.Linear(mid_dim, action_dim)
|
|
)
|
|
self.a_logstd = nn.Parameter(torch.zeros((1, action_dim)) - 0.5, requires_grad=True)
|
|
self.sqrt_2pi_log = np.log(np.sqrt(2 * np.pi))
|
|
|
|
if self.layer_norm:
|
|
self.apply_layer_norm()
|
|
|
|
def apply_layer_norm(self):
|
|
def init_weights(layer):
|
|
if isinstance(layer, nn.Linear):
|
|
nn.init.orthogonal_(layer.weight, 1.0)
|
|
nn.init.constant_(layer.bias, 0.0)
|
|
|
|
self.net.apply(init_weights)
|
|
|
|
def forward(self, state):
|
|
return self.net(state).tanh()
|
|
|
|
def get_action(self, state):
|
|
a_avg = self.forward(state)
|
|
a_std = self.a_logstd.exp()
|
|
noise = torch.randn_like(a_avg)
|
|
action = a_avg + noise * a_std
|
|
return action, noise
|
|
|
|
def get_logprob_entropy(self, state, action):
|
|
a_avg = self.forward(state)
|
|
a_std = self.a_logstd.exp()
|
|
delta = ((a_avg - action) / a_std).pow(2) * 0.5
|
|
logprob = -(self.a_logstd + self.sqrt_2pi_log + delta).sum(1)
|
|
dist_entropy = (logprob.exp() * logprob).mean()
|
|
return logprob, dist_entropy
|
|
|
|
def get_old_logprob(self, _action, noise):
|
|
delta = noise.pow(2) * 0.5
|
|
return -(self.a_logstd + self.sqrt_2pi_log + delta).sum(1)
|
|
|
|
|
|
class CriticAdv(nn.Module):
|
|
def __init__(self, mid_dim, state_dim, _action_dim, layer_norm=False):
|
|
super().__init__()
|
|
self.layer_norm = layer_norm
|
|
self.net = nn.Sequential(
|
|
nn.Linear(state_dim, mid_dim), nn.ReLU(),
|
|
nn.Linear(mid_dim, mid_dim), nn.ReLU(),
|
|
nn.Linear(mid_dim, mid_dim), nn.Hardswish(),
|
|
nn.Linear(mid_dim, 1)
|
|
)
|
|
if self.layer_norm:
|
|
self.apply_layer_norm()
|
|
|
|
def apply_layer_norm(self):
|
|
def init_weights(layer):
|
|
if isinstance(layer, nn.Linear):
|
|
nn.init.orthogonal_(layer.weight, 1.0)
|
|
nn.init.constant_(layer.bias, 0.0)
|
|
|
|
self.net.apply(init_weights)
|
|
|
|
def forward(self, state):
|
|
return self.net(state)
|
|
|
|
|
|
class AgentPrimalDualPPO:
|
|
def __init__(self):
|
|
self.state = None
|
|
self.device = None
|
|
self.action_dim = None
|
|
self.get_obj_critic = None
|
|
|
|
self.criterion = torch.nn.SmoothL1Loss()
|
|
self.cri = self.cri_target = self.if_use_cri_target = self.cri_optim = self.ClassCri = None
|
|
self.act = self.act_target = self.if_use_act_target = self.act_optim = self.ClassAct = None
|
|
|
|
self.ClassCri = CriticAdv
|
|
self.ClassAct = ActorPPO
|
|
|
|
self.ratio_clip = 0.2
|
|
self.lambda_entropy = 0.02
|
|
self.lambda_gae_adv = 0.98
|
|
self.get_reward_sum = None
|
|
self.trajectory_list = None
|
|
|
|
self.lambda_cost = 1.0 # 初始对偶变量
|
|
self.constraint_value = 1.0 # 约束值，例如安全成本限制
|
|
|
|
def init(self, net_dim, state_dim, action_dim, learning_rate=1e-4, if_use_gae=False, gpu_id=0, layer_norm=False):
|
|
self.device = torch.device(f"cuda:{gpu_id}" if (torch.cuda.is_available() and (gpu_id >= 0)) else "cpu")
|
|
self.trajectory_list = list()
|
|
self.get_reward_sum = self.get_reward_sum_gae if if_use_gae else self.get_reward_sum_raw
|
|
|
|
self.cri = self.ClassCri(net_dim, state_dim, action_dim, layer_norm).to(self.device)
|
|
self.act = self.ClassAct(net_dim, state_dim, action_dim, layer_norm).to(
|
|
self.device) if self.ClassAct else self.cri
|
|
self.cri_target = deepcopy(self.cri) if self.if_use_cri_target else self.cri
|
|
self.act_target = deepcopy(self.act) if self.if_use_act_target else self.act
|
|
|
|
self.cri_optim = torch.optim.Adam(self.cri.parameters(), learning_rate)
|
|
self.act_optim = torch.optim.Adam(self.act.parameters(), learning_rate) if self.ClassAct else self.cri
|
|
|
|
def select_action(self, state):
|
|
states = torch.as_tensor((state,), dtype=torch.float32, device=self.device)
|
|
actions, noises = self.act.get_action(states)
|
|
return actions[0].detach().cpu().numpy(), noises[0].detach().cpu().numpy()
|
|
|
|
def explore_env(self, env, target_step):
|
|
state = self.state
|
|
trajectory_temp = list()
|
|
last_done = 0
|
|
for i in range(target_step):
|
|
action, noise = self.select_action(state)
|
|
state, next_state, reward, done, cost = env.step(np.tanh(action))
|
|
trajectory_temp.append((state, reward, done, action, noise, cost))
|
|
if done:
|
|
state = env.reset()
|
|
last_done = i
|
|
else:
|
|
state = next_state
|
|
self.state = state
|
|
|
|
trajectory_list = self.trajectory_list + trajectory_temp[:last_done + 1]
|
|
self.trajectory_list = trajectory_temp[last_done:]
|
|
return trajectory_list
|
|
|
|
def update_net(self, buffer, batch_size, repeat_times, soft_update_tau):
|
|
with torch.no_grad():
|
|
buf_len = buffer[0].shape[0]
|
|
buf_state, buf_action, buf_noise, buf_reward, buf_mask, buf_cost = [ten.to(self.device) for ten in buffer]
|
|
|
|
buf_value = torch.cat([self.cri_target(buf_state[i:i + 4096]) for i in range(0, buf_len, 4096)], dim=0)
|
|
buf_logprob = self.act.get_old_logprob(buf_action, buf_noise)
|
|
|
|
buf_r_sum, buf_advantage = self.get_reward_sum(buf_len, buf_reward, buf_mask, buf_value)
|
|
buf_advantage = (buf_advantage - buf_advantage.mean()) / (buf_advantage.std() + 1e-5)
|
|
|
|
cost_sum = buf_cost.sum().item()
|
|
if cost_sum > self.constraint_value:
|
|
self.lambda_cost += 0.01 * (cost_sum - self.constraint_value)
|
|
else:
|
|
self.lambda_cost -= 0.01 * (self.constraint_value - cost_sum)
|
|
self.lambda_cost = max(self.lambda_cost, 0)
|
|
|
|
obj_critic = obj_actor = None
|
|
for _ in range(int(buf_len / batch_size * repeat_times)):
|
|
indices = torch.randint(buf_len, size=(batch_size,), requires_grad=False, device=self.device)
|
|
state = buf_state[indices]
|
|
action = buf_action[indices]
|
|
r_sum = buf_r_sum[indices]
|
|
logprob = buf_logprob[indices]
|
|
advantage = buf_advantage[indices]
|
|
|
|
new_logprob, obj_entropy = self.act.get_logprob_entropy(state, action)
|
|
ratio = (new_logprob - logprob.detach()).exp()
|
|
surrogate1 = advantage * ratio
|
|
surrogate2 = advantage * ratio.clamp(1 - self.ratio_clip, 1 + self.ratio_clip)
|
|
obj_surrogate = -torch.min(surrogate1, surrogate2).mean()
|
|
obj_actor = obj_surrogate + obj_entropy * self.lambda_entropy - self.lambda_cost * buf_cost[indices].mean()
|
|
self.optim_update(self.act_optim, obj_actor)
|
|
|
|
value = self.cri(state).squeeze(1)
|
|
obj_critic = self.criterion(value, r_sum)
|
|
self.optim_update(self.cri_optim, obj_critic)
|
|
if self.cri_target is not self.cri:
|
|
self.soft_update(self.cri_target, self.cri, soft_update_tau)
|
|
|
|
a_std_log = getattr(self.act, 'a_std_log', torch.zeros(1))
|
|
return obj_critic.item(), obj_actor.item(), a_std_log.mean().item()
|
|
|
|
def get_reward_sum_raw(self, buf_len, buf_reward, buf_mask, buf_value) -> (torch.Tensor, torch.Tensor):
|
|
buf_r_sum = torch.empty(buf_len, dtype=torch.float32, device=self.device)
|
|
pre_r_sum = 0
|
|
for i in range(buf_len - 1, -1, -1):
|
|
buf_r_sum[i] = buf_reward[i] + buf_mask[i] * pre_r_sum
|
|
pre_r_sum = buf_r_sum[i]
|
|
buf_advantage = buf_r_sum - (buf_mask * buf_value[:, 0])
|
|
return buf_r_sum, buf_advantage
|
|
|
|
def get_reward_sum_gae(self, buf_len, ten_reward, ten_mask, ten_value) -> (torch.Tensor, torch.Tensor):
|
|
buf_r_sum = torch.empty(buf_len, dtype=torch.float32, device=self.device)
|
|
buf_advantage = torch.empty(buf_len, dtype=torch.float32, device=self.device)
|
|
pre_r_sum = 0
|
|
pre_advantage = 0
|
|
for i in range(buf_len - 1, -1, -1):
|
|
buf_r_sum[i] = ten_reward[i] + ten_mask[i] * pre_r_sum
|
|
pre_r_sum = buf_r_sum[i]
|
|
buf_advantage[i] = ten_reward[i] + ten_mask[i] * (pre_advantage - ten_value[i])
|
|
pre_advantage = ten_value[i] + buf_advantage[i] * self.lambda_gae_adv
|
|
return buf_r_sum, buf_advantage
|
|
|
|
@staticmethod
|
|
def optim_update(optimizer, objective):
|
|
optimizer.zero_grad()
|
|
objective.backward()
|
|
optimizer.step()
|
|
|
|
@staticmethod
|
|
def soft_update(target_net, current_net, tau):
|
|
for tar, cur in zip(target_net.parameters(), current_net.parameters()):
|
|
tar.data.copy_(cur.data * tau + tar.data * (1.0 - tau))
|
|
|
|
|
|
class Arguments:
|
|
def __init__(self, agent=None, env=None):
|
|
self.agent = agent # Deep Reinforcement Learning algorithm
|
|
self.env = env # the environment for training
|
|
self.cwd = None # current work directory. None means set automatically
|
|
self.if_remove = False # remove the cwd folder? (True, False, None:ask me)
|
|
self.visible_gpu = '0' # for example: os.environ['CUDA_VISIBLE_DEVICES'] = '0, 2,'
|
|
# self.worker_num = 2 # rollout workers number pre GPU (adjust it to get high GPU usage)
|
|
self.num_threads = 32 # cpu_num for evaluate model, torch.set_num_threads(self.num_threads)
|
|
|
|
'''Arguments for training'''
|
|
self.num_episode = 1000 # to control the train episodes for PPO
|
|
self.gamma = 0.995 # discount factor of future rewards
|
|
self.learning_rate = 2 ** -14 # 2e-4
|
|
self.soft_update_tau = 2 ** -8 # 2 ** -8 ~= 5e-3
|
|
|
|
self.net_dim = 256 # the network width
|
|
self.batch_size = 4096 # num of transitions sampled from replay buffer.
|
|
self.repeat_times = 2 ** 3 # collect target_step, then update network
|
|
self.target_step = 4096 # repeatedly update network to keep critic's loss small
|
|
self.max_memo = self.target_step # capacity of replay buffer
|
|
self.if_per_or_gae = False # GAE for on-policy sparse reward: Generalized Advantage Estimation.
|
|
|
|
'''Arguments for evaluate'''
|
|
self.random_seed = 0 # initialize random seed in self.init_before_training()
|
|
# self.random_seed_list = [1234, 2234, 3234, 4234, 5234]
|
|
self.random_seed_list = [1234]
|
|
self.train = True
|
|
self.save_network = True
|
|
self.test_network = True
|
|
self.save_test_data = True
|
|
self.compare_with_gurobi = True
|
|
self.plot_on = True
|
|
|
|
def init_before_training(self, if_main):
|
|
if self.cwd is None:
|
|
agent_name = self.agent.__class__.__name__
|
|
self.cwd = f'./{agent_name}'
|
|
|
|
if if_main:
|
|
import shutil # remove history according to bool(if_remove)
|
|
if self.if_remove is None:
|
|
self.if_remove = bool(input(f"| PRESS 'y' to REMOVE: {self.cwd}? ") == 'y')
|
|
elif self.if_remove:
|
|
shutil.rmtree(self.cwd, ignore_errors=True)
|
|
print(f"| Remove cwd: {self.cwd}")
|
|
os.makedirs(self.cwd, exist_ok=True)
|
|
|
|
np.random.seed(self.random_seed)
|
|
torch.manual_seed(self.random_seed)
|
|
torch.set_num_threads(self.num_threads)
|
|
torch.set_default_dtype(torch.float32)
|
|
|
|
os.environ['CUDA_VISIBLE_DEVICES'] = str(self.visible_gpu)
|
|
|
|
|
|
def update_buffer(_trajectory):
|
|
_trajectory = list(map(list, zip(*_trajectory))) # 2D-list transpose, here cut the trajectory into 5 parts
|
|
ten_state = torch.as_tensor(_trajectory[0]) # tensor state here
|
|
ten_reward = torch.as_tensor(_trajectory[1], dtype=torch.float32)
|
|
# _trajectory[2] = done, replace done by mask, save memory
|
|
ten_mask = (1.0 - torch.as_tensor(_trajectory[2], dtype=torch.float32)) * gamma
|
|
ten_action = torch.as_tensor(_trajectory[3])
|
|
ten_noise = torch.as_tensor(_trajectory[4], dtype=torch.float32)
|
|
|
|
buffer[:] = (ten_state, ten_action, ten_noise, ten_reward, ten_mask) # list store tensors
|
|
|
|
_steps = ten_reward.shape[0] # how many steps are collected in all trajectories
|
|
_r_exp = ten_reward.mean() # the mean reward
|
|
return _steps, _r_exp
|
|
|
|
|
|
if __name__ == '__main__':
|
|
args = Arguments()
|
|
reward_record = {'episode': [], 'steps': [], 'mean_episode_reward': [], 'unbalance': []}
|
|
loss_record = {'episode': [], 'steps': [], 'critic_loss': [], 'actor_loss': [], 'entropy_loss': []}
|
|
args.visible_gpu = '0'
|
|
for seed in args.random_seed_list:
|
|
args.random_seed = seed
|
|
args.agent = AgentPrimalDualPPO()
|
|
|
|
agent_name = f'{args.agent.__class__.__name__}'
|
|
args.agent.cri_target = True
|
|
args.env = ESSEnv()
|
|
args.init_before_training(if_main=True)
|
|
agent = args.agent
|
|
env = args.env
|
|
agent.init(args.net_dim, env.state_space.shape[0], env.action_space.shape[0], args.learning_rate,
|
|
args.if_per_or_gae, layer_norm=True)
|
|
|
|
cwd = args.cwd
|
|
gamma = args.gamma
|
|
batch_size = args.batch_size # how much data should be used to update net
|
|
target_step = args.target_step # how many steps of one episode should stop
|
|
repeat_times = args.repeat_times # how many times should update for one batch size data
|
|
soft_update_tau = args.soft_update_tau
|
|
agent.state = env.reset()
|
|
buffer = list()
|
|
num_episode = args.num_episode
|
|
|
|
if args.train:
|
|
for i_episode in range(num_episode):
|
|
with torch.no_grad():
|
|
trajectory_list = []
|
|
for _ in range(target_step):
|
|
current_obs = agent.state
|
|
action, noise = agent.select_action(current_obs)
|
|
next_obs, reward, done, info, cost = env.step(action)
|
|
trajectory_list.append((current_obs, reward, done, action, noise, cost))
|
|
agent.state = next_obs
|
|
if done:
|
|
break
|
|
steps, r_exp = update_buffer(trajectory_list)
|
|
critic_loss, actor_loss, entropy_loss = agent.update_net(buffer, batch_size, repeat_times, soft_update_tau)
|
|
loss_record['critic_loss'].append(critic_loss)
|
|
loss_record['actor_loss'].append(actor_loss)
|
|
loss_record['entropy_loss'].append(entropy_loss)
|
|
|
|
with torch.no_grad():
|
|
episode_reward, episode_unbalance = get_episode_return(env, agent.act, agent.device)
|
|
reward_record['mean_episode_reward'].append(episode_reward)
|
|
reward_record['unbalance'].append(episode_unbalance)
|
|
print(f'current episode is {i_episode}, reward: {episode_reward}, unbalance: {episode_unbalance}')
|
|
|
|
act_save_path = f'{args.cwd}/actor.pth'
|
|
loss_record_path = f'{args.cwd}/loss_data.pkl'
|
|
reward_record_path = f'{args.cwd}/reward_data.pkl'
|
|
|
|
with open(loss_record_path, 'wb') as tf:
|
|
pickle.dump(loss_record, tf)
|
|
with open(reward_record_path, 'wb') as tf:
|
|
pickle.dump(reward_record, tf)
|
|
|
|
if args.save_network:
|
|
torch.save(agent.act.state_dict(), act_save_path)
|
|
print('actor parameters have been saved')
|
|
|
|
if args.test_network:
|
|
args.cwd = agent_name
|
|
agent.act.load_stateDict(torch.load(act_save_path))
|
|
print('parameters have been reloaded and test')
|
|
record = test_one_episode(env, agent.act, agent.device)
|
|
eval_data = pd.DataFrame(record['system_info'])
|
|
eval_data.columns = ['time_step', 'price', 'netload', 'action', 'real_action', 'soc', 'battery', 'gen1', 'gen2',
|
|
'gen3', 'temperature', 'irradiance', 'unbalance', 'operation_cost']
|
|
if args.save_test_data:
|
|
test_data_save_path = f'{args.cwd}/test_data.pkl'
|
|
with open(test_data_save_path, 'wb') as tf:
|
|
pickle.dump(record, tf)
|
|
|
|
'''compare with gurobi data and results'''
|
|
if args.compare_with_gurobi:
|
|
month = record['init_info'][0][0]
|
|
day = record['init_info'][0][1]
|
|
initial_soc = record['init_info'][0][3]
|
|
base_result = optimization_base_result(env, month, day, initial_soc)
|
|
if args.plot_on:
|
|
from plotDRL import PlotArgs, make_dir, plot_evaluation_information, plot_optimization_result
|
|
|
|
plot_args = PlotArgs()
|
|
plot_args.feature_change = 'primal_dual'
|
|
args.cwd = agent_name
|
|
plot_dir = make_dir(args.cwd, plot_args.feature_change)
|
|
plot_optimization_result(base_result, plot_dir)
|
|
plot_evaluation_information(args.cwd + '/' + 'test_data.pkl', plot_dir)
|
|
'''compare the different cost get from gurobi and PPO'''
|
|
ration = sum(eval_data['operation_cost']) / sum(base_result['step_cost'])
|
|
print('operation_cost_sum:', sum(eval_data['operation_cost']))
|
|
print('step_cost_sum:', sum(base_result['step_cost']))
|
|
print('ration:', ration)
|