From the 1 of 4 linked papers with an AI index.
4 papers
Explaining Reinforcement Learning Agents via Inductive Logic Programming
Celeste Veronese, Edoardo Zorzi, Daniele Meli +1
The paper proposes using Inductive Logic Programming to extract symbolic rules from reinforcement learning policies and introduces objective metrics to quantify how explainable tho…
Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation
Edoardo Zorzi, Francesco Taioli, Yiming Wang +4
We propose Question-Asking Navigation (QAsk-Nav), the first reproducible benchmark for Collaborative Instance Object Navigation (CoIN) that enables an explicit, separate assessment…
Seldonian Reinforcement Learning for Ad Hoc Teamwork
Edoardo Zorzi, Alberto Castellini, Leonidas Bakopoulos +2
Most offline RL algorithms return optimal policies but do not provide statistical guarantees on desirable behaviors. This could generate reliability issues in safety-critical appli…
Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues
Francesco Taioli, Edoardo Zorzi, Gianni Franchi +4
Language-driven instance object navigation assumes that human users initiate the task by providing a detailed description of the target instance to the embodied agent. While this d…