Abstract
Developments in reinforcement learning (RL) have allowed algorithms to achieve impressive performance in highly complex, but largely static problems. In contrast, biological learning seems to value efficiency of adaptation to a constantly-changing world. Here we build on a recently-proposed neuronal learning rule that assumes each neuron can optimize its energy balance by predicting its own future activity. That assumption leads to a neuronal learning rule that uses presynaptic input to modulate prediction error. We argue that an analogous RL rule would use action probability to modulate reward prediction error. This modulation makes the agent more sensitive to negative experiences, and more careful in forming preferences. We embed the proposed rule in both tabular and deep-Q-network RL algorithms, and find that it outperforms conventional algorithms in simple, but highly-dynamic tasks. We suggest that the new rule encapsulates a core principle of biological intelligence; an important component for allowing algorithms to adapt to change in a human-like way.
Abstract (translated)
URL
https://arxiv.org/abs/2205.09729
