Autonomous agents that execute human tasks by controlling computers can enhance human
productivity and application accessibility. However, progress in this field will be driven by …

The ability to combine known skills to create new ones may be crucial in the solution of
complex reinforcement learning problems that unfold over extended periods. We argue that a …

We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To
this end, we evaluate their performance on pairs of existing math word problems together so …

StarCraft II is one of the most challenging simulated reinforcement learning environments; it
is partially observable, stochastic, multi-agent, and mastering StarCraft II requires strategic …

StarCraft II is one of the most challenging reinforcement learning (RL) environments; it is
partially observable, stochastic, and multi-agent, and mastering StarCraft II requires strategic …

This work studies a central extremal graph theory problem inspired by a 1975 conjecture of
Erd\H{o}s, which aims to find graphs with a given size (number of nodes) that maximize the …

Reinforcement learning (RL) is a very powerful approach for learning good control strategies
from data. Value functions are a key concept for reinforcement learning, as they guide the …

… have obviously been influenced by one or the other, so at this point I think is fair to say that
this work, and the past and the future ones, also belong to Daniel Toyama and Sara Campos. …

Understanding cell morphogenesis during metazoan development requires knowledge of
how cells and the extracellular matrix produce and respond to forces. We investigated how …

A graph Γ is called an n-Cayley graph over a group G if there exists a semiregular subgroup
of Aut (Γ) that is isomorphic to G with n orbits (of equal size). This is one of the …