6 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…
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…
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…
Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment
Nathan Gavenski, Matteo Leonetti, Odinaldo Rodrigues
State-of-the-art imitation learning from observation methods (ILfO) have recently made significant progress, but they still have some limitations: they need action-based supervised…
Quantifying Generalisation in Imitation Learning
Nathan Gavenski, Odinaldo Rodrigues
Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking…