We tested these results in a biomechanically simplified setting & found that this completely breaks down, underlining that these different neural "solutions" actually depend on a more complex output-state maps. This sheds a new light on the idea of "universal solutions" for neural networks.

Finally, we show that the neural representations produced by RL have stabilization properties when fine-tuning to new environmental dynamics. Unlike supervised learning, this leads to representational reorganization that mirrors cortical plasticity in monkeys.