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.

169,291 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · May 201919922001200920182026
1 result for “DQN-URBE”
A Bayesian Approach to Robust Reinforcement Learningcs.LG

Bayesian approach improves learning in RMDPs with faster adaptation.

problem Learning robust policies in RMDPs with changing or adversarial dynamics.
method Introduce Uncertainty Robust Bellman Equation (URBE) and DQN-URBE algorithm.
result URBE-based strategy leads to better trade-off between robustness and exploration.
Bayesian Reinforcement LearningRobust Markov Decision ProcessesAdaptive Uncertainty SetsDQN-URBEOnline Adaptation
2019-05-20abs ↗pdf ↗