Scaling Learning based Policy Optimization for Temporal Tasks via Dropout

arXiv:2403.15826v1 Announce Type: cross
Abstract: This paper introduces a model-based approach for training feedback controllers for an autonomous agent operating in a highly nonlinear environment. We desire the trained policy to ensure that the agent satisfies specific task objectives, expressed in discrete-time Signal Temporal Logic (DT-STL). One advantage for reformulation of a task via formal frameworks, like DT-STL, is that it permits quantitative satisfaction semantics. In other words, given a trajectory and a DT-STL formula, we can compute the robustness, …

abstract agent arxiv autonomous cs.ai cs.lg cs.ro cs.sy dropout eess.sy environment feedback logic optimization paper policy scaling signal stl tasks temporal training type via