Showing 2026Show all
2 papers · 1 filter
cs.RO2026
Discriminative Barrier Functions for Safe Adversarial Imitation Learning from Observation
Anubhav Vishwakarma, Bhaumik Mehta, Caleb Hsu +3
Inverse Reinforcement Learning (IRL) algorithms are powerful tools for learning from and generalizing expert demonstrations, but they often rely on unconstrained exploration, rende…
cs.RO2026
Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation
Tyler Han, Bat Nemekhbold, Siyang Shen +6
Current methods in robot learning are fundamentally bottlenecked by one or more of: hand-designed rewards, simulation modeling, or action supervision (e.g. teleoperation) each requ…