# Initialize actor, critic, target networks and optimizers
actor = Actor(state_dim, action_dim, max_action)
critic = Critic(state_dim, action_dim)
target_actor = Actor(state_dim, action_dim, max_action)
target_critic = Critic(state_dim, action_dim)
# Copy weights from actor to target_actor, and critic to target_critic
target_actor.load_state_dict(actor.state_dict())
target_critic.load_state_dict(critic.state_dict())
target_actor.eval()
target_critic.eval()

actor_optimizer = optim.Adam(actor.parameters(), lr=1e-3)
critic_optimizer = optim.Adam(critic.parameters(), lr=1e-3)
buffer = ReplayBuffer(capacity=100000)