'Rating' object is not subscriptable

[trangml]

Found an issue with the OpenSkillRating which causes Wandb logging to fail in the policy ranker.

Problem is here

PufferLib/pufferlib/policy_ranker.py

Line 90 in 889f172

f"skillrank/{wandb_policy}/mu": rating['mu'],

Exception has occurred: TypeError       (note: full exception trace is shown but execution is paused at: _run_module_as_main)
'Rating' object is not subscriptable
  File "/home/mtrang/anaconda3/envs/nmmo/lib/python3.9/site-packages/pufferlib/policy_ranker.py", line 90, in update_ranks
    f"skillrank/{wandb_policy}/mu": rating["mu"],
  File "/home/mtrang/Documents/rl/neural_mmo/baselines/reinforcement_learning/clean_pufferl.py", line 394, in evaluate
    self.policy_ranker.update_ranks(
  File "/home/mtrang/anaconda3/envs/nmmo/lib/python3.9/site-packages/pufferlib/utils.py", line 223, in wrapper
    result = func(*args, **kwargs)
  File "/home/mtrang/Documents/rl/neural_mmo/baselines/train_optuna.py", line 66, in objective
    _, stats, infos = trainer.evaluate()
  ...
TypeError: 'Rating' object is not subscriptable``

Simple fix of

                wandb.log({
                    f"skillrank/{wandb_policy}/mu": rating.mu,
                    f"skillrank/{wandb_policy}/sigma": rating.sigma,
                    f"skillrank/{wandb_policy}/score": scores[wandb_policy],
                    "agent_steps": step,
                    "global_step": step,
                })

worked for me.