Edmund

Results 2 comments of Edmund

[RLlib] PPO reset_config() AttributeError: 'dict' object has no attribute '_enable_new_api_stack'

Any updates on this?

[Bug] TQC Hyperparameter optimization: Results do not match the reference. This is likely a bug/unexpected loss of precision.

I did this again with an new version of jax (jaxlib 0.4.23 cuda120py310h3cc97ca_20) and it gives a new error now: ''' [I 2024-04-07 15:55:02,691] A new study created in memory...