Neuroevolution Results in Emergence of Short-Term Memory for Goal-Directed Behavior
This work addresses the challenge of adaptive behavior in neuroscience and adaptive systems, though it appears incremental as it builds on existing neuroevolution approaches.
The researchers tackled the problem of understanding goal-directed behavior in multi-goal environments by developing an evolutionary model using a neuroevolutionary algorithm based on neuron duplication. The simulation results showed that agents evolved short-term memory capabilities, with two specific mechanisms emerging: integration of sensory signals and internal activity for action specialization, and slow neurodynamical processes for coding previous choices.
Animals behave adaptively in the environment with multiply competing goals. Understanding of the mechanisms underlying such goal-directed behavior remains a challenge for neuroscience as well for adaptive system research. To address this problem we developed an evolutionary model of adaptive behavior in the multigoal stochastic environment. Proposed neuroevolutionary algorithm is based on neuron's duplication as a basic mechanism of agent's recurrent neural network development. Results of simulation demonstrate that in the course of evolution agents acquire the ability to store the short-term memory and, therefore, use it in behavioral strategies with alternative actions. We found that evolution discovered two mechanisms for short-term memory. The first mechanism is integration of sensory signals and ongoing internal neural activity, resulting in emergence of cell groups specialized on alternative actions. And the second mechanism is slow neurodynamical processes that makes possible to code the previous behavioral choice.