activity
20242026
collaborators

7 papers

cs.LG2026

Active Inference as a Convex Markov Decision Process

Nikola Milosevic, Nicolás Hinrichs, Nico Scherf

Active Inference (AIF) frames adaptive behavior as the minimization of expected free energy (EFE), combining epistemic and pragmatic objectives within a single variational principl…

cs.LG2026

Stochastic Decision Horizons for Constrained Reinforcement Learning

Nikola Milosevic, Leonard Franz, Daniel Haeufle +3

We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint satisfaction, a desirable property…

cs.LG2025

The Geometry of Nonlinear Reinforcement Learning

Nikola Milosevic, Nico Scherf

Reward maximization, safe exploration, and intrinsic motivation are often studied as separate objectives in reinforcement learning (RL). We present a unified geometric framework, t…

cond-mat.soft2025

Physical Embodiment Enables Information Processing Beyond Explicit Sensing in Active Matter

Diptabrata Paul, Nikola Milosevic, Nico Scherf +1

Living microorganisms have evolved dedicated sensory machinery to detect environmental perturbations, processing these signals through biochemical networks to guide behavior. Repli…

cs.LG2025

Central Path Proximal Policy Optimization

Nikola Milosevic, Johannes Müller, Nico Scherf

In constrained Markov decision processes, enforcing constraints during training is often thought of as decreasing the final return. Recently, it was shown that constraints can be i…

cs.LG2025

Embedding Safety into RL: A New Take on Trust Region Methods

Nikola Milosevic, Johannes Müller, Nico Scherf

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constra…