QMIX

class QMIX(agent_model, qmixer_model, double_q=True, gamma=0.99, lr=0.0005, clip_grad_norm=None)

基类：parl.core.paddle.algorithm.Algorithm

__init__(agent_model, qmixer_model, double_q=True, gamma=0.99, lr=0.0005, clip_grad_norm=None)

QMIX algorithm :param agent_model: agents’ local q network for decision making. :type agent_model: parl.Model :param qmixer_model: A mixing network which takes local q values as input

to construct a global Q network double_q (bool): Double-DQN gamma (float): discounted factor for reward computation. lr (float): learning rate. clip_grad_norm (None, or float): clipped value of gradients’ global norm.

learn(state_batch, actions_batch, reward_batch, terminated_batch, obs_batch, available_actions_batch, filled_batch)

参数

• state_batch (paddle.Tensor) – (batch_size, T, state_shape)

• actions_batch (paddle.Tensor) – (batch_size, T, n_agents)

• reward_batch (paddle.Tensor) – (batch_size, T, 1)

• terminated_batch (paddle.Tensor) – (batch_size, T, 1)

• obs_batch (paddle.Tensor) – (batch_size, T, n_agents, obs_shape)

• available_actions_batch (paddle.Tensor) – (batch_size, T, n_agents, n_actions)

• filled_batch (paddle.Tensor) – (batch_size, T, 1)

返回

train loss td_error (float): train TD error

返回类型

loss (float)