in agents/bc_w.py [0:0]
def __init__(self,
state_dim,
action_dim,
max_action,
device,
discount,
tau,
lr=3e-4,
hidden_sizes=[256,256],
w_gamma=5.0,
c_iter=3,
):
self.actor = Actor(state_dim, action_dim, max_action,
device=device,
hidden_sizes=hidden_sizes,
layer_norm=False).to(device)
self.actor_optimizer = torch.optim.Adam(self.actor.parameters(), lr=lr)
self.critic = Critic(state_dim, action_dim).to(device)
self.critic_optimizer = torch.optim.Adam(self.critic.parameters(), lr=1e-4)
self.max_action = max_action
self.action_dim = action_dim
self.discount = discount
self.tau = tau
self.device = device
self.w_gamma = w_gamma
self.c_iter = c_iter