Evaluating Actuators in a Purely Information-Theory Based Reward Model
This work addresses a specific bottleneck in robot cognitive architectures, offering an incremental improvement for researchers in AI and robotics.
The paper tackles the problem of evaluating actuators in AGINAO's cognitive engine by proposing a model that measures the impact of effector activation and sensor feedback on the average reward of processing units, moving beyond the previous information-theory based reward model that was ineffective for actuators.
AGINAO builds its cognitive engine by applying self-programming techniques to create a hierarchy of interconnected codelets - the tiny pieces of code executed on a virtual machine. These basic processing units are evaluated for their applicability and fitness with a notion of reward calculated from self-information gain of binary partitioning of the codelet's input state-space. This approach, however, is useless for the evaluation of actuators. Instead, a model is proposed in which actuators are evaluated by measuring the impact that an activation of an effector, and consequently the feedback from the robot sensors, has on average reward received by the processing units.