Explorative imitation learning: A path signature approach for continuous environments

N Gavenski, J Monteiro, F Meneguzzi, M Luck… - ECAI 2024, 2024 - ebooks.iospress.nl
Some imitation learning methods combine behavioural cloning with self-supervision to infer
actions from state pairs. However, most rely on a large number of expert trajectories to …

How resilient are imitation learning methods to sub-optimal experts?

N Gavenski, J Monteiro, A Medronha… - Brazilian Conference on …, 2022 - Springer
Imitation Learning (IL) algorithms try to mimic expert behavior in order to be capable of
performing specific tasks, but it remains unclear what those strategies could achieve when …

Self-Supervised Adversarial Imitation Learning

J Monteiro, N Gavenski, F Meneguzzi… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
Behavioural cloning is an imitation learning technique that teaches an agent how to behave
via expert demonstrations. Recent approaches use self-supervision of fully-observable …

Imitation Learning: A Survey of Learning Methods, Environments and Metrics

N Gavenski, O Rodrigues, M Luck - arXiv preprint arXiv:2404.19456, 2024 - arxiv.org
Imitation learning is an approach in which an agent learns how to execute a task by trying to
mimic how one or more teachers perform it. This learning approach offers a compromise …

[PDF][PDF] A Survey of Imitation Learning Methods, Environments and Metrics

N Gavenski, F Meneguzzi, M Luck, O Rodrigues - 2024 - aura.abdn.ac.uk
Imitation learning is a socially-inspired machine learning approach that consists of learning
a task from examples provided by a teacher. In other words, this approach refers to an …