Sampling is an important research problem in statistics learning with many applications such as Bayesian inference [1], multi-arm bandit optimization [2], and reinforcement learning [3].

Reinforcement learning utilizing kernel ridge regression to predict the expected value function represents a powerful method with great representational capacity. This setting is a highly versatile framework amenable to analytical results. Weconsider kernel-based function approximation for RL in the infinite horizon average reward setting, also referred toasthe undiscounted setting. Wepropose an optimistic algorithm, similar to acquisition function based algorithms in the special caseofbandits.

Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the modelled agents during execution. To eliminate this assumption, we extract representations from thelocalinformation ofthecontrolled agent using encoderdecoderarchitectures.

The modeling of ideal transition function inI2Q isfully decentralized and independent from the learned policies of other agents, helping I2Q be free from non-stationarity and learn the optimal policy.