diff --git a/ding/rl_utils/tests/test_ppo.py b/ding/rl_utils/tests/test_ppo.py index 973a9f0be8c32ee48c0cf47c60e6244613afdd0a..bab78c148548965dd5021cc4e19a1df8764b3751 100644 --- a/ding/rl_utils/tests/test_ppo.py +++ b/ding/rl_utils/tests/test_ppo.py @@ -70,7 +70,7 @@ def test_mappo(): @pytest.mark.parametrize('use_value_clip, dual_clip, weight', args) def test_ppo_error_continous(use_value_clip, dual_clip, weight): B, N = 4, 6 - mu_sigma_new = [torch.randn(B, N).requires_grad_(True), torch.randn(B, N).requires_grad_(True)] + mu_sigma_new = [torch.rand(B, N).requires_grad_(True), torch.rand(B, N).requires_grad_(True)] mu_sigma_old = [ mu_sigma_new[0] + torch.rand_like(mu_sigma_new[0]) * 0.1, mu_sigma_new[1] + torch.rand_like(mu_sigma_new[1]) * 0.1