Agent Probing Interaction Policies [article]

Siddharth Ghiya, Oluwafemi Azeez, Brendan Miller
2019 arXiv   pre-print
Reinforcement learning in a multi agent system is difficult because these systems are inherently non-stationary in nature. In such a case, identifying the type of the opposite agent is crucial and can help us address this non-stationary environment. We have investigated if we can employ some probing policies which help us better identify the type of the other agent in the environment. We've made a simplifying assumption that the other agent has a stationary policy that our probing policy is
more » ... ng to approximate. Our work extends Environmental Probing Interaction Policy framework to handle multi agent environments.
arXiv:1911.09535v3 fatcat:g3c3chnofffbngvdh4u6kt3odm