Inferring and Conveying Intentionality: Beyond Numerical Rewards to Logical Intentions
This work addresses the challenge of developing conscious AI agents for collaboration and reasoning, but it appears incremental as it builds on existing inverse reinforcement learning methods with logical extensions.
The paper tackled the problem of inferring and conveying shared intentionality in AI agents by formulating it as an inverse reinforcement learning problem with logical reward specifications, and demonstrated the approach on a simple grid-world example.
Shared intentionality is a critical component in developing conscious AI agents capable of collaboration, self-reflection, deliberation, and reasoning. We formulate inference of shared intentionality as an inverse reinforcement learning problem with logical reward specifications. We show how the approach can infer task descriptions from demonstrations. We also extend our approach to actively convey intentionality. We demonstrate the approach on a simple grid-world example.