A micro-genesis account of longer-form reinforcement learning in structured and unstructured environments

We explored the possibility that in order for longer-form expressions of reinforcement learning (win-calmness, loss-restlessness) to manifest across tasks, they must first develop because of micro-transactions within tasks. We found no evidence of win-calmness or loss-restlessness when wins could not be maximised (unexploitable opponents), nor when the threat of win minimisation was presented (exploiting opponents), but evidence of win-calmness (but not loss-restlessness) when wins could be maximised (exploitable opponents).

Automated summary

The study suggests that longer-form expressions of reinforcement learning, such as win-calmness and loss-restlessness, may manifest across tasks, but only when wins can be maximized.