MARTI-4: new model of human brain, considering neocortex and basal ganglia -- learns to play Atari game by reinforcement learning on a single CPU
This work addresses the challenge of developing more efficient and biologically plausible AI models for reinforcement learning tasks, though it appears incremental in its approach.
The authors tackled the problem of creating a biologically-inspired AI model by introducing MARTI, a new model of the human brain that incorporates neocortex and basal ganglia, which learned to play Atari games using reinforcement learning on a single CPU in several hours.
We present Deep Control - new ML architecture of cortico-striatal brain circuits, which use whole cortical column as a structural element, instead of a singe neuron. Based on this architecture, we present MARTI - new model of human brain, considering neocortex and basal ganglia. This model is de-signed to implement expedient behavior and is capable to learn and achieve goals in unknown environments. We introduce a novel surprise feeling mechanism, that significantly improves reinforcement learning process through inner rewards. We use OpenAI Gym environment to demonstrate MARTI learning on a single CPU just in several hours.