AI RESEARCH
Robust Remote Reinforcement Learning over Unreliable Communication Channels using Homomorphic State Encoding
arXiv CS.LG
•
ArXi:2508.07722v2 Announce Type: replace Traditional Reinforcement Learning (RL) frameworks generally assume that the agent perceives the state of the underlying Marko process instantaneously and then takes actions accordingly. If the agent cannot directly observe the process, but rather receives state updates from a remote sensor over a lossy and/or delayed channel, it may be forced to operate with partial and intermittent information.