def __init__(self, state_dim, action_dim, cfg):
self.action_dim = action_dim
self.state_dim = state_dim
self.loss = 0
self.gamma = cfg.gamma
self.frame_idx = 0 # 用于epsilon的衰减计数
self.epsilon = lambda frame_idx: cfg.epsilon_end + (cfg.epsilon_start - cfg.epsilon_end) * math.exp(-1. * frame_idx / cfg.epsilon_decay)
self.batch_size = cfg.batch_size
self.device = cfg.device
self.policy_net = MLP(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
self.target_net = MLP(state_dim, action_dim, cfg.hidden_dim).to(cfg.device)
self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr)
self.memory = ReplayBuffer(cfg.memory_capacity)
def __init__(self, state_dim, action_dim, cfg):
self.action_dim = action_dim # 总的动作个数
self.device = cfg.device # 设备，cpu或gpu等
self.gamma = cfg.gamma # 奖励的折扣因子
# e-greedy策略相关参数
self.frame_idx = 0 # 用于epsilon的衰减计数
self.epsilon = lambda frame_idx: cfg.epsilon_end + \
(cfg.epsilon_start - cfg.epsilon_end) * \
math.exp(-1. * frame_idx / cfg.epsilon_decay)
self.batch_size = cfg.batch_size
self.policy_net = MLP(state_dim, action_dim,hidden_dim=cfg.hidden_dim).to(self.device)
self.target_net = MLP(state_dim, action_dim,hidden_dim=cfg.hidden_dim).to(self.device)
for target_param, param in zip(self.target_net.parameters(),self.policy_net.parameters()): # copy params from policy net
target_param.data.copy_(param.data)
self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr)
self.memory = ReplayBuffer(cfg.memory_capacity)
def __init__(self, state_dim, action_dim, cfg):
self.action_dim = action_dim # 总的动作个数
self.device = cfg.device # 设备，cpu或gpu等
self.gamma = cfg.gamma
# e-greedy策略相关参数
self.actions_count = 0
self.epsilon_start = cfg.epsilon_start
self.epsilon_end = cfg.epsilon_end
self.epsilon_decay = cfg.epsilon_decay
self.batch_size = cfg.batch_size
self.policy_net = MLP(state_dim, action_dim,
hidden_dim=cfg.hidden_dim).to(self.device)
self.target_net = MLP(state_dim, action_dim,
hidden_dim=cfg.hidden_dim).to(self.device)
# target_net的初始模型参数完全复制policy_net
self.target_net.load_state_dict(self.policy_net.state_dict())
self.target_net.eval() # 不启用 BatchNormalization 和 Dropout
# 可查parameters()与state_dict()的区别，前者require_grad=True
self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr)
self.loss = 0
self.memory = ReplayBuffer(cfg.memory_capacity)
def __init__(self, state_dim, action_dim, cfg):
self.state_dim = state_dim
self.action_dim = action_dim
self.gamma = cfg.gamma
self.device = cfg.device
self.batch_size = cfg.batch_size
self.frame_idx = 0
self.epsilon = lambda frame_idx: cfg.epsilon_end + (
cfg.epsilon_start - cfg.epsilon_end) * math.exp(-1. * frame_idx /
cfg.epsilon_decay)
self.policy_net = MLP(2 * state_dim, action_dim,
cfg.hidden_dim).to(cfg.device)
self.meta_policy_net = MLP(state_dim, state_dim, cfg.hidden_dim).to(
cfg.device) # 高层策略用于产生高层指导动作，输出动作分布等价于状态分布
self.optimizer = optim.Adam(self.policy_net.parameters(), lr=cfg.lr)
self.meta_optimizer = optim.Adam(self.meta_policy_net.parameters(),
lr=cfg.lr)
self.memory = ReplayBuffer(cfg.memory_capacity)
self.meta_memory = ReplayBuffer(cfg.memory_capacity)
self.loss_numpy = 0
self.meta_loss_numpy = 0
self.losses = []
self.meta_losses = []