Skip to content

Author

Michael Amir

We have 4 of 10 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Nov 2026

Leave It Better Than Found: Value-Guided Cooperation in Sequential Tasks

We consider the problem of sequential task continuation, where one robot acts in a workspace that has been affected by a previous robot. Current approaches in multi-robot cooperation rely heavily on co-training or co-optimization, assumingthat the robots have access to collective interaction data during the policy trai...

Mario Gómez Andreu, Michael Amir, Antonio Marino et al. · 0 citations
Review Oct 2026

Learning Robot Metareasoning: Adaptive Computation Budgets for Real-Time Control

Across ground-robot navigation, agile quadrotor flight, and contact-rich manipulation, the learned policy changes its budget with the demands of the scenario, discovering efficient reasoning patterns that outperform fixed-budget baselines.

Lorenzo Magnino, Antonio Marino, Michael Amir et al. · 0 citations
#artificial intelligence Preprint Oct 2026

GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories

GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game. Analogously, in multi-robot coordination, individual robots may need to forgo locally reward-maximising behaviours to improve overall team performance. Such self-sacrificial behaviou...

Rishabh Jain, A. Moldagalieva, Lorenzo Magnino et al. · 0 citations
Preprint Sep 2026

Games Over Observation Spaces in Multi-Agent Capture the Flag

A Double Oracle algorithm is proposed to find approximate empirical equilibria to solve this intractably large Capture the Flag game, and it is empirically validated that observation manipulation can improve the defense's performance.

Mae Frost, Michael Amir, S. Bopardikar · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.