Paper
Object Files and Schemata: Factorizing Declarative and Procedural\n Knowledge in Dynamical Systems
Modeling a structured, dynamic environment like a video game requires keeping\ntrack of the objects and their states declarative knowledge) as well as\npredicting how objects behave (procedural knowledge). Black-box models with a\nmonolithic hidden state often fail to apply procedural knowledge consistently\nand uniformly, i.e., they lack systematicity. For example, in a video game,\ncorrect prediction of one enemy's trajectory does not ensure correct prediction\nof another's. We address this issue via an architecture that factorizes\ndeclarative and procedural knowledge and that imposes modularity within each\nform of knowledge. The architecture consists of active modules called object\nfiles that maintain the state of a single object and invoke passive external\nknowledge sources called schemata that prescribe state updates. To use a video\ngame as an illustration, two enemies of the same type will share schemata but\nwill have separate object files to encode their distinct state (e.g., health,\nposition). We propose to use attention to determine which object files to\nupdate, the selection of schemata, and the propagation of information between\nobject files. The resulting architecture is a drop-in replacement conforming to\nthe same input-output interface as normal recurrent networks (e.g., LSTM, GRU)\nyet achieves substantially better generalization on environments that have\nmultiple object tokens of the same type, including a challenging intuitive\nphysics benchmark.\n
Authors: Goyal, Anirudh · Lamb, Alex · Gampa, Phanideep · Beaudoin, Philippe · Levine, Sergey · Blundell, Charles · Bengio, Yoshua · Mozer, Michael