565 citations · 571 across the 10 of their papers we have counts for
8 papers · 1 filter
Code to Control: Synthesizing Parameterized Reactive Controllers
Zergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1
Recent LLM-based approaches to control either invoke a language model to select actions or synthesize world models that require planning at every decision, introducing latency that…
Induction and Inquiry via Probabilistic Reasoning over Language and Code
Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld +2
How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must…
DiG-bench: Discovery in Games
Ruairidh M. Battleday, Kai Sandbrink, Jimi Cullen-Drohan +13
Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark landscape, with few…
Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents
Zergham Ahmed, Kazuki Irie, Joshua B. Tenenbaum +2
Humans learn abstractions and use them to plan efficiently to quickly generalize across tasks -- an ability that remains challenging for state-of-the-art large language model (LLM)…
ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
Yichao Liang, Dat Nguyen, Cambridge Yang +7
Long-horizon embodied planning is challenging because the world does not only change through an agent's actions: exogenous processes (e.g., water heating, dominoes cascading) unfol…
LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
Aidan Curtis, Hao Tang, Thiago Veloso +4
Partially Observable Markov Decision Processes (POMDPs) model decision making under uncertainty. While there are many approaches to approximately solving POMDPs, we aim to address…
Synthesizing world models for bilevel planning
Zergham Ahmed, Joshua B. Tenenbaum, Christopher J. Bates +1
Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human…
VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning
Yichao Liang, Nishanth Kumar, Hao Tang +5
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensori…