Mirco Mutti
@mircomutti.bsky.social
Reinforcement learning, but without rewards.
Postdoc at the Technion. PhD from Politecnico di Milano.
https://muttimirco.github.io
Postdoc at the Technion. PhD from Politecnico di Milano.
https://muttimirco.github.io
Humans typically develop a standard strategy prescribing a sequence of tests to diagnose the condition before committing to the best treatment (see img left). Can we design a bandit algorithm that learns a similarly interpretable exploration but it's also provably efficient?
3/n
3/n
July 15, 2025 at 3:50 PM
Humans typically develop a standard strategy prescribing a sequence of tests to diagnose the condition before committing to the best treatment (see img left). Can we design a bandit algorithm that learns a similarly interpretable exploration but it's also provably efficient?
3/n
3/n
If interested on our take on addressing inverse RL in large state spaces, go to meet @filippo_lazzati and @alberto_metelli in the poster session 5 #NeurIPS2024 today (paper -> arxiv.org/abs/2406.03812)
December 13, 2024 at 2:33 PM
If interested on our take on addressing inverse RL in large state spaces, go to meet @filippo_lazzati and @alberto_metelli in the poster session 5 #NeurIPS2024 today (paper -> arxiv.org/abs/2406.03812)