It is shown that memory traps can arise both from overgeneralizations in memory writing, and when acting on memory, and thus motivate the need for new research into ensuring that agents preserve the scope of their memories.
Kaiqu Liang, J. F. Fisac, Thomas L. Griffiths et al.· 1 citation
Reinforcement learning in safety-critical domains requires maximizing task performance while strictly adhering to safety constraints. Existing safe reinforcement learning paradigms typically force a trade-off: they either require a priori knowledge to provide strict safety guarantees (e.g., safety filters), or they ena...
Nishanth Rao, Royina Karegoudra Jayanth, Benjamin Eysenbach et al.· 0 citations
This work formalizes RL safety with a safety-critical Markov decision process (SC-MDP), which requires categorical, rather than high-probability, avoidance of catastrophic failure states and provides a simple, principled recipe for safe RL: train and deploy RL policies with the most permissive safety filter that is ava...
Donggeon David Oh, D. Nguyen, Hai-Min Hu et al.· Proceedings of IASEAI Confer...· 5 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.