ROFeb 25, 2021
Theory and Analysis of Optimal Planning over Long and Infinite Horizons for Achieving Independent Partially-Observable Tasks that Evolve over Time
arXiv:2102.12633v11 citations
Originality Synthesis-oriented
AI Analysis
This addresses the challenge of planning under uncertainty for dynamic tasks, but appears incremental as it builds on a recently developed algorithm.
The paper tackles the problem of optimal planning for multiple independent, partially observable tasks that evolve over time, providing theoretical analysis and proofs for an algorithm that achieves this over long and infinite horizons.
We present the theoretical analysis and proofs of a recently developed algorithm that allows for optimal planning over long and infinite horizons for achieving multiple independent tasks that are partially observable and evolve over time.