At the moment, WandbLogger is always using wandb.init with monitor_gym =
True.
This fails when OpenAI's gym is not installed, which doesn't make sense
after the transition to Gymnasium.
I am using Tianshou with non-standard RL environment, which adhere to
Gymnasium API, and the current code is throwing exceptions.
I suggest to make it a controllable parameter. I left the default value
to True (to make it functionally the same for people using gym). It may
also make sense to change the default to False.
* Use `global_step` as the x-axis for wandb
* Use Tensorboard SummaryWritter as core with `wandb.init(..., sync_tensorboard=True)`
* Update all atari examples with wandb
Co-authored-by: Jiayi Weng <trinkle23897@gmail.com>
