3 papers
cs.LG2026
What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
Julia Barth, Armin Sommer, Kunvar Thaman +1
Goal misgeneralization is a common failure mode in which an agent behaves competently out of distribution but does not pursue the intended goal. However, we still have a weak under…
cs.LG2026
Reinforced Planning with Latent World Models
Armin Sommer, Jannik Schilling
Humans solve complex problems by constructing plans and mentally simulating their outcomes with an internal model of the world. Machine learning has made substantial progress in le…
cs.LG2026
Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States
Armin Sommer
Reinforcement learning is conventionally divided into model-based and model-free methods. In this taxonomy, model-based methods perform lookahead planning over a learned world mode…