88 citations · 339 across the 67 of their papers we have counts for
4 papers · 1 filter
Dynamic Shielding for Reinforcement Learning in Black-Box Environments
Masaki Waga, Ezequiel Castellano, Sasinee Pruekprasert +3
It is challenging to use reinforcement learning (RL) in cyber-physical systems due to the lack of safety guarantees during learning. Although there have been various proposals to r…
Control-Data Separation and Logical Condition Propagation for Efficient Inference on Probabilistic Programs
Ichiro Hasuo, Yuichiro Oyabu, Clovis Eberhart +3
We present a novel sampling framework for probabilistic programs. The framework combines two recent ideas -- \emph{control-data separation} and \emph{logical condition propagation}…
Predictive PER: Balancing Priority and Diversity towards Stable Deep Reinforcement Learning
Sanghwa Lee, Jaeyoung Lee, Ichiro Hasuo
Prioritized experience replay (PER) samples important transitions, rather than uniformly, to improve the performance of a deep reinforcement learning agent. We claim that such prio…
Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spaces
Takamasa Okudono, Masaki Waga, Taro Sekiyama +1
We present a method to extract a weighted finite automaton (WFA) from a recurrent neural network (RNN). Our algorithm is based on the WFA learning algorithm by Balle and Mohri, whi…