We thank the reviewers for their careful reading and insightful comments. We will add this in the final version. Transformer-based) models to further shrink the search space. Number of nodes in the graphs seems to be quite low ( 200 for GNMT). Is there some manual grouping operation performed on the computational graph?

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.

Maximum cardinality bipartite matching is an important graph optimization problem with several applications.

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.

The industry practice has been moving to embedding based retrieval (EBR).

Given such a setup, a natural question to ask is how does one measure the performance of the learner? Classical online learning studies one such notion of performance known as regret.

Qualcomm AI Research is an initiative of Qualcomm Technologies, Inc. Work completed during employment at Qualcomm Technologies, Inc. 36th Conference on Neural Information Processing Systems (NeurIPS 2022). of the Directed Acyclic Graph (DAG) that encodes the precedence constraints, which induces a Combinatorial Optimization [3] (CO) problem which is in general computationally hard [4].

Policy Learning (ConPoLe) that explicitly optimizes the InfoNCE loss, which lower bounds the mutual information between the current state and next states that continue on a path to the solution.