Riccardo Zamboni
@ricczamboni.bsky.social
PhD candidate @polimi | Reinforcement Learning @rl3polimi | I do stuff, I see stuff. Some with purpose, most by chance.
https://ricczamboni.github.io
https://ricczamboni.github.io
Very nice and neat! If you happen to be at RLC @kale-ab.bsky.social will present our position paper on a slightly related topic! (Post to come, I was asked not to release any spoiler)
July 23, 2025 at 8:33 AM
Very nice and neat! If you happen to be at RLC @kale-ab.bsky.social will present our position paper on a slightly related topic! (Post to come, I was asked not to release any spoiler)
Do not worry about that, you will get free money!
July 19, 2025 at 11:31 PM
Do not worry about that, you will get free money!
(4/N) Then, we also show how this diversification enforces experience diversity and better performances in downstream tasks!
July 8, 2025 at 2:05 PM
(4/N) Then, we also show how this diversification enforces experience diversity and better performances in downstream tasks!
(3/N) First, we show *how* to properly enforce behavioral diversity with parallel agents throught the lenses of Maximum State Entropy. The trick? Optimize over the *right* state distribution🎛️!
July 8, 2025 at 2:05 PM
(3/N) First, we show *how* to properly enforce behavioral diversity with parallel agents throught the lenses of Maximum State Entropy. The trick? Optimize over the *right* state distribution🎛️!
(2/N) If you can collect data on many parallel environments, would you rather use single common policy or a set of diverse, specialized ones?
July 8, 2025 at 2:05 PM
(2/N) If you can collect data on many parallel environments, would you rather use single common policy or a set of diverse, specialized ones?
Hi! I’d be happy to join these cool folks :)
November 27, 2024 at 11:52 PM
Hi! I’d be happy to join these cool folks :)
Would be happy to join :)
November 27, 2024 at 11:43 PM
Would be happy to join :)