Mean_value plot in Total_reward - Interpretation

[SunilaAkbar]

Hi,

Can I please ask that what does Mean_value plot and also its significance in reinforcement learning (specific to this algorithm). I tried to understand this from the code but couldn't.

Also, to interpret the results, should we look at the results with zero smoothing or with 0.8/0.9 smoothing with reference to reinforcement learning?

The response will highly be appreciated.

Best Wishes!