Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Feb 202019922001200920172026
1 result for “SymNet”
Symbolic Network: Generalized Neural Policies for Relational MDPscs.LG

SymNet uses neural models to solve RMDPs efficiently.

problem Limited effectiveness of generalized policies in RMDPs.
method SymNet trains shared parameters for an RDDL domain, converts instances to graphs, uses relational neural models for node embeddings, and scores actions based on embeddings.
result SymNet policies outperform random and state-of-the-art deep reactive policies on nine RDDL domains.
Relational Markov Decision ProcessesSymNetNeural PoliciesRDDLGeneralized Policies
2020-02-18abs ↗pdf ↗