Benjamin Heymann @benhey.bsky.social · 04/02/2026😀 "On the impact of the utility in semivalue-based data valuation", with Mélissa Tamine, Patrick Loiseau and Maxime Vono as been accepted to ICLR 2026. Link below 111
Benjamin Heymann @benhey.bsky.social · 19/09/2025extended abstracts are on my website: benhey.github.iobenhey.github.io Benjamin Heymann A simple, whitespace theme for academics. Based on [*folio](https://github.com/bogoli/-folio) design. 010
Benjamin Heymann @benhey.bsky.social · 19/09/2025The programme is here sites.google.com/view/consequ...sites.google.comCONSEQUENCES 2025 - ProgrammeSeptember 22nd 2025 - Room D3 11:30 – 11:35 Welcome by the organisers 11:35 – 12:30 Tutorial: Practical Bandits: An Industry Perspective Bram van den Akker, Olivier Jeunen, Ben London and... 110
Benjamin Heymann @benhey.bsky.social · 19/09/2025My team will present 5 accepted submissions at CONSEQUENCES next week during the RecSys25 conference 😊 😊 😊 232
Reposted by Benjamin Heymannalexandregilotte.bsky.social @alexandregilotte.bsky.social · 01/06/2025Our latest update to Gobs and Gods is live, just in time for #TurnBasedThursdayFest tomorrow. Hope you have fun! store.steampowered.com/news/app/250... #indiegame #turnbasedfest #gobsstore.steampowered.comGobs and Gods - Gobs and Gods 1.3: More Mobs and Monsters! - Steam NewsWe are thrilled to announce the release of the next big update to Gobs and Gods, focusing on enhancing tactical combat and diversifying enemies. 052
Benjamin Heymann @benhey.bsky.social · 23/05/2025📍Poster: 10am 🎤 Talk: 11:30am 📄 Paper: arxiv.org/abs/2409.03875 If you're at #AAMAS2025, come by and say hi to @sharky6000.bsky.social! And let us know what you think! 🤝 6/6arxiv.orgLearning in Games with Progressive HidingWhen learning to play an imperfect information game, it is often easier to first start with the basic mechanics of the game rules. For example, one can play several example rounds with private cards r... 040
Benjamin Heymann @benhey.bsky.social · 23/05/2025To our knowledge, this is the first use of information relaxation techniques from operations research in computational game theory. We're excited to see how this perspective bridges communities! #AAMAS2025 #ReinforcementLearning #MultiAgentSystems 5/6 131
Benjamin Heymann @benhey.bsky.social · 23/05/2025🧠 The idea: 1️⃣ Train as if all information is visible 2️⃣ Penalize the agent for using “forbidden” info (hide it) This enables fast learning of policies that respect information constraints. Hence: Progressive Hiding. 4/6 120
Benjamin Heymann @benhey.bsky.social · 23/05/2025If you've played cooperative imperfect-information games like Hanabi or The Crew, you know how hard they are. For an AI with no inter-game communication and no perfect recall? Even harder! That’s where Progressive Hiding comes in. 🔍 3/6 140
Benjamin Heymann @benhey.bsky.social · 23/05/2025Inspired by the classic Progressive Hedging algorithm by Rockafellar & Wets (1991), our method brings similar ideas to multi-agent learning. That paper has 2000+ citations — and we’re excited to adapt it to game theory! #AAMAS #AI #GameTheory 2/6 120
Benjamin Heymann @benhey.bsky.social · 23/05/2025🎉 Super excited: today @sharky6000.bsky.social is presenting our new algorithm Progressive Hiding at #AAMAS2025! It's a learning method for games with imperfect information. 🔗 See his post: bsky.app/profile/shar... Wish I could be there! 😢 1/6 174
Benjamin Heymann @benhey.bsky.social · 23/05/2025Today, Marc @sharky6000.bsky.social his going to present our paper "learning in games with progressive hiding". 120
Reposted by Benjamin HeymannMarc Lanctot @sharky6000.bsky.social · 23/05/2025Day #5 and last day 😭 @aamasconf.bsky.social We'll be presenting one more paper called "Learning in Games with Progressive Hiding" by @benhey.bsky.social and myself. Poster @ 10am, talk @ 11:30am. arxiv.org/abs/2409.03875 This is an application of progressive hedging to learning in games: 1/2 1133
Benjamin Heymann @benhey.bsky.social · 22/05/2025Hope everything went well. Thank you Marc!!!!!!!!!! 110
Reposted by Benjamin HeymannMarc Lanctot @sharky6000.bsky.social · 20/05/2025The first, at GAIW at 9:55 is "Adaptive Preference Aggregation" by Benjamin Heymann. This paper proposes a way to adapt a recent urn process algorithm that implements maximal lotteries (by Brandl and @felix-brandt.bsky.social '24) to the setting of user-conditional alignment/recommendation. 2/N 231
Reposted by Benjamin HeymannMarc Lanctot @sharky6000.bsky.social · 21/05/2025@sanmayd.bsky.social at @aamasconf.bsky.social opening ceremonies asking the important questions. Is it pronounced "Ay-MAS" or "Ah-MAS"? I've always said Ay-MAS but I am already outvoted by both Michael Wellman and Eugene Vorobeychik! 😱😱😱 Discuss! 461
Reposted by Benjamin HeymannAAMAS.2027 @aamasconf.bsky.social · 28/02/2025Join Us for AAMAS 2025 in Detroit! Registration Now Open! We are excited to announce that registration for AAMAS 2025 is now open! Don’t miss out — register today at aamas2025.org/index.php/co.... See you in Detroit! 🚀aamas2025.orgRegistration – AAMAS 2025 Detroit 1167
