4 papers
PR-Smoother: Simulator-Preserving Non-Gaussian Smoothing for Data Assimilation
Yuta Tarumi
Many physical data assimilation (DA) workflows require smoothing methods that represent non-Gaussian posteriors over physical state variables, scale to high-dimensional simulators,…
Adaptive Problem Generation via Symbolic Representations
Teresa Yeo, Myeongho Jeon, Dulaj Weerakoon +4
We present a method for generating training data for reinforcement learning with verifiable rewards to improve small open-weights language models on mathematical tasks. Existing da…
EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
Zhening Li, Armando Solar-Lezama, Yisong Yue +1
We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core…
When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
Zhening Li, Gabriel Poesia, Armando Solar-Lezama
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an envi…