Search is an important technique in program synthesis that allows for adaptive strategies such as focusing on particular search directions based on execution results. Several prior works have demonstrated that neural models are effective at guiding program synthesis searches.

We give a model-based agent that builds a Python program representing its knowledge of the world based on its interactions with the environment.

Reinforcement learning with the help of neural-guided search consumes huge computational resources to achieve remarkable performance.

Notably, we offer fresh perspectives on how neural solvers can handle VRP constraints.

It is more memory-efficient than Adam as it only keeps track of the momentum. Different from adaptive optimizers, its update has the same magnitude for each parameter calculated through the sign operation. We compare Lion with widely used optimizers, such as Adam and Adafactor, for training a variety of models on different tasks. On image classification, Lion boosts the accuracy of ViT by up to 2% on ImageNet and saves up to 5x the pre-training compute on JFT.

To this end, we introduce Poppy, a simple training procedure for populations.