cs.IT, cs.LG, cs.MA, math.IT

Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding

arXiv:2508.07722v2 Announce Type: replace
Abstract: Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Markov process instantaneously and then takes actions accordingly. If the agen…