Towards A Theory-Of-Mind-Inspired Generic Decision-Making Framework
This work addresses the challenge of generic decision-making in complex environments for AI agents, but it appears incremental as it builds on existing simulation techniques and focuses on a specific game context.
The authors tackled the problem of applying simulation-based decision-making in complex dynamic environments by proposing a theory-of-mind-inspired generic framework, and they demonstrated its effectiveness by achieving results comparable to the IJCAI2013 AIBirds contest benchmark.
Simulation is widely used to make model-based predictions, but few approaches have attempted this technique in dynamic physical environments of medium to high complexity or in general contexts. After an introduction to the cognitive science concepts from which this work is inspired and the current development in the use of simulation as a decision-making technique, we propose a generic framework based on theory of mind, which allows an agent to reason and perform actions using multiple simulations of automatically created or externally inputted models of the perceived environment. A description of a partial implementation is given, which aims to solve a popular game within the IJCAI2013 AIBirds contest. Results of our approach are presented, in comparison with the competition benchmark. Finally, future developments regarding the framework are discussed.