6 papers
Bounded Ratio Reinforcement Learning
Yunke Ao, Le Chen, Bruce D. Lee +5
Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However…
Computational Arbitrage in AI Model Markets
Ricardo Olmedo, Bernhard Schölkopf, Moritz Hardt
Consider a market of competing model providers selling query access to models with varying costs and capabilities. Customers submit problem instances and are willing to pay up to a…
A Critical Perspective on Finite Sample Conformal Prediction Theory in Medical Applications
Klaus-Rudolf Kladny, Bernhard Schölkopf, Lisa Koch +2
Machine learning (ML) is transforming healthcare, but safe clinical decisions demand reliable uncertainty estimates that standard ML models fail to provide. Conformal prediction (C…
Natural Building Blocks for Structured World Models: Theory, Evidence, and Scaling
Lancelot Da Costa, Sanjeev Namjoshi, Mohammed Abbas Ansari +1
The field of world modeling is fragmented, with researchers developing bespoke architectures that rarely build upon each other. We propose a framework that specifies the natural bu…
Learning Nonlinear Causal Reductions to Explain Reinforcement Learning Policies
Armin Kekić, Jan Schneider, Dieter Büchler +2
Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. In this w…
Towards Embodiment Scaling Laws in Robot Locomotion
Bo Ai, Liu Dai, Nico Bohlinger +7
Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodim…