Happy
Happy
When I was using your code, I only founded the Hyperparameters of Walker-Walk but Humanoid-Walk. In the official paper, it has the results of Humanoid-Walk Environment. So could you please...
When I try the karman vortex case, I want to calculate from a given ndarray. such as: velocity_field = np.random.rand(128, 128, 2) velocity_repeat = np.repeat(velocity_field[np.newaxis, :, :, :], repeats=10, axis=0)...
When I was using your code, I only founded the Hyperparameters of Walker-Walk but Humanoid-Walk. In the official paper, it has the results of Humanoid-Walk Environment. So could you please...
I would like to ask whether ppo_mini_batch_size and ppo_micro_batch_size have a big impact on GPU usage? And in the process of PPO training, which parameters have a greater impact on...
### Feature request Does Qwen3-30B-A3B-Instruct-2507 support using sglang rollout in verl? If not, where should I change for supporting it? If so, is there an example case? ### Motivation Use...