8 papers
ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
Juarez Monteiro, Nathan Gavenski, Guilherme Lima +3
Reinforcement learning agents operating under partial observability must act on incomplete information, making them natural candidates for guidance from small language models (SLMs…
When in Doubt, Plan It Out: Committed Small Language Model Deliberation for Reactive Reinforcement Learning
Nathan Gavenski, Juarez Monteiro, Francisco Galuppo +2
Reinforcement Learning (RL) policies often degrade in unfamiliar environments because they lack explicit deliberation. We propose Plan, Align, Commit, Think (PACT), a hybrid archit…
Zero-Shot Goal Recognition with Large Language Models
Kin Max Piamolini Gusmão, Nathan Gavenski, Nir Oren +1
Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather th…
Online Goal Recognition using Path Signature and Dynamic Time Warping
Douglas Tesch, Nathan Gavenski, Leonardo Amado +2
Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Recent work addresses these chal…
When to ASK: Uncertainty-Gated Language Assistance for Reinforcement Learning
Juarez Monteiro, Nathan Gavenski, Gianlucca Zuin +1
Reinforcement learning (RL) agents often struggle with out-of-distribution (OOD) scenarios, leading to high uncertainty and random behavior. While language models (LMs) contain val…
Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
Nathan Gavenski, Felipe Meneguzzi, Odinaldo Rodrigues
Imitation learning stands at a crossroads: despite decades of progress, current imitation learning agents remain sophisticated memorisation machines, excelling at replay but failin…