Such direct sim2real transfer is not guaranteed to succeed, however, and in cases where it fails, it is unclear how to best utilize the simulator. In this work, we show that in many regimes, while direct sim2real transfer may fail, we can utilize the simulator to learn a set of exploratory policies which enable efficient exploration in the real world.

Let's consider a two-party communication problem where the sender wants to transmit some data

Concretely, we prove that polynomial-sized message-passing GNN's can learn the

Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters. An important open problem is the design of computationally efficient data-driven algorithms for combinatorial algorithm families with multiple parameters.

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

Logical Credal Networks or LCNs were recently introduced as a powerful probabilistic logic framework for representing and reasoning with imprecise knowledge.

This paper uses chess, a landmark planning problem in AI, to assess transformers'

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or intermediate reasoning).