However, its application to Q-learning has been limited due to the presence of the max-operator, which makes the associated ODE model a complex nonlinear system. In contrast, the associated ODE of TD learning for policy evaluation is a linear system, whose asymptotic stability is much easier to analyze in general.

We thank all reviewers for their useful feedback and acknowledgement of our contribution. We first answer some common questions brought up by reviewers. Richer numerical evidence will be included in the revision. Below we address the each reviewer's comments separately. We leave this extension for future investigation.

Similarly, Multiagent RL (MARL) can also be accelerated if agents can share knowledge with each other.

Lookahead search has been a critical component of recent AI successes, such as in the games of chess, go, and poker. However, the search methods used in these games, and in many other settings, are tabular. Tabular search methods do not scale well with the size of the search space, and this problem is exacerbated by stochasticity and partial observability. In this work we replace tabular search with online model-based fine-tuning of a policy neural network via reinforcement learning, and show that this approach outperforms state-of-the-art search algorithms in benchmark settings. In particular, we use our search algorithm to achieve a new state-of-the-art result in self-play Hanabi, and show the generality of our algorithm by also showing that it outperforms tabular search in the Atari game Ms. Pacman.

This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space. This framework yields a general setting that permits discrete and continuous control inputs as well as non-smooth, non-differentiable dynamics.