Questions about training.

Hi,
I trained on the single test motion clip `data/motion/test.bvh` with default configuration in `test_env_humanoid_imitation.yaml`. The total reward does not increase after 12 hours training. However, the character still fall. I wonder if there are some parameters in configuration need to be tuned.

commond:
`python rllib_driver.py --mode train --spec data/spec/test_env_humanoid_imitation.yaml --project_dir ./`

reward:

test results:

Thanks !

Reproduce the report with data/motion/test.bvh, data/spec/test_env_humanoid_imitation.yaml, and the command using rllib_driver.py. Inspect the training output and reward plot alongside the falling-character result; the issue provides no parameter target or defined success condition beyond improved reward and a character that does not fall.

Written by the indexing model from the issue text.