"...positive reinforcement leads the model to make more sustainable changes, changes which can become consistent patterns and persist for long periods of time.
In contrast, while negative reinforcement also makes a behavior more likely to occur, it is used for maintaining a minimum performance standard rather than reaching a modelβs maximum performance. Negative reinforcement in reinforcement learning can help ensure that a model is kept away from undesirable actions, but it canβt really make a model explore desired actions."
In AI we have already found that:
[excerpt from linked article]
"...positive reinforcement leads the model to make more sustainable changes, changes which can become consistent patterns and persist for long periods of time.
In contrast, while negative reinforcement also makes a behavior more likely to occur, it is used for maintaining a minimum performance standard rather than reaching a modelβs maximum performance. Negative reinforcement in reinforcement learning can help ensure that a model is kept away from undesirable actions, but it canβt really make a model explore desired actions."
The same applies to people.