LGAISYMLJun 12, 2020

Similarity-based transfer learning of decision policies

arXiv:2006.08768v11 citations
Originality Synthesis-oriented
AI Analysis

This addresses policy learning for decision-making systems, but appears incremental as it builds on existing FPD formalism.

The paper tackles the problem of learning decision policies from past experience by proposing a new general approach using the Fully Probabilistic Design formalism to find a stochastic policy.

A problem of learning decision policy from past experience is considered. Using the Fully Probabilistic Design (FPD) formalism, we propose a new general approach for finding a stochastic policy from the past data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes