Safety is critical to broadening the application of reinforcement learni...
In an offline reinforcement learning setting, the safe policy improvemen...
We study Markov decision processes (MDPs), where agents have direct cont...
This position paper reflects on the state-of-the-art in decision-making ...
We study safe policy improvement (SPI) for partially observable Markov
d...
Deep Reinforcement Learning (RL) agents are susceptible to adversarial n...
We address the problem of safe reinforcement learning from pixel
observa...
Markov decision processes (MDPs) are formal models commonly used in
sequ...
Previous work has shown the unreliability of existing algorithms in the ...