bug in reinforce with baseline #37
Description
the update value network should be:
alpha_w = 1e-3 # 初始化 optimizer_w = optim.Adam(**s_value_func**.parameters(), lr=alpha_w) optimizer_w.zero_grad() policy_loss_w =-delta policy_loss_w.backward(retain_graph = True) clip_grad_norm_(policy_loss_w, 0.1) optimizer_w.step()