Abstract: The disclosed method and system involves training an autonomous AI agent using simulation models that incorporate temporal progression in decision-making. The method begins with ingesting system operation data, which includes receiving historical data in a time series sequence and identifying observation sensor and action variables. The data is checked for simulation readiness, and any time gaps in the sequence are addressed by segmenting the data into batches to exclude these gaps. The segmented data is then mapped to a framework for time-based models that account for temporal progression. These models are trained using the mapped data, and a simulation of the system is generated based on the trained models. The trained time-based models are discretized and shaped to fit a decision-making process, which is then used to train the autonomous AI agent. This approach ensures the agent's decision-making is informed by temporal dynamics within the system.

Abstract: A platform for developing autonomous AI agents capable of intelligent behavior includes a simulation environment for creating AI trainable simulations, an agent shell configurator for customizing agent frameworks, a sensor configurator for feedback provision, a perceptor configurator for processing sensor variables, a scenario configurator for training variability, and a skills configurator for task-specific expertise. These components are used to create untrained autonomous AI agents with sensor, perceptor, scenario, and skills modules, along with performable actions. A training module dynamically transforms untrained AI agents into trained ones through training exercises, and a deployment module exports trained AI agents as executable code or file artifact. When deployed in real-world systems, the trained autonomous AI agents exhibit intelligent behavior by perceiving environments, autonomously taking actions, and improving performance through learning based on real-world expertise data.

Abstract: A system and method are provided for identifying and outputting data characterizing the behavior exhibited by an autonomous AI agent. The method involves tracking behavior iterations of the autonomous AI agent interacting with an environment during a training or run cycle, collecting iteration data, and transforming the data into an explanation of the behavior exhibited by the agent at different levels of granularity. This transformation includes identifying behavior data for individual iterations, grouping data by episodes representing subsets of all iterations, and capturing behavior data across the entirety of the training or run cycle. The method outputs the data characterizing the behavior exhibited by the autonomous AI agent, providing insights into its performance and learning processes.