Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems
This addresses the challenge of efficient task generalization in networked multi-agent systems, though it appears incremental as it builds on existing LSOC principles.
The paper tackles the problem of generalizing optimal control from learned component tasks to unlearned composite tasks in Multi-Agent Systems (MASs) by using the linearity composition principle of linearly solvable optimal control, achieving compositionality and optimality in a sample-efficient manner that reduces re-computation burden.
In this paper, we discuss the methodology of generalizing the optimal control law from learned component tasks to unlearned composite tasks on Multi-Agent Systems (MASs), by using the linearity composition principle of linearly solvable optimal control (LSOC) problems. The proposed approach achieves both the compositionality and optimality of control actions simultaneously within the cooperative MAS framework in both discrete- and continuous-time in a sample-efficient manner, which reduces the burden of re-computation of the optimal control solutions for the new task on the MASs. We investigate the application of the proposed approach on the MAS with coordination between agents. The experiments show feasible results in investigated scenarios, including both discrete and continuous dynamical systems for task generalization without resampling.