7 papers
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment
Filippo Tonini, Federico Torrielli, Anton Danholt Lautrup +3
As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiating, and acting on shared tas…
Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies
Magnus Victor Boock, Abdullah Akgül, Mustafa Mert Çelikok +1
We present a new operator-theoretic representation learning framework for offline reinforcement learning that recovers the directed temporal geometry of a controlled Markov process…
Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates
Manuel Haußmann, Manuel Haussmann, Mustafa Mert Çelikok +1
Fitted Q-iteration (FQI) is well understood when the data come from a fixed distribution and the action set is finite, whereas value-based continuous control collects its data adap…
Distributional Active Inference
Abdullah Akgül, Gulcin Baykal, Manuel Haußmann +2
Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted…
SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments
Hüseyin Aydın, Kevin Godin-Dubois, Libio Goncalvez Braz +6
Reinforcement learning (RL) offers a general approach for modeling and training AI agents, including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared Human…
Differentiable User Models
Alex Hämäläinen, Mustafa Mert Çelikok, Samuel Kaski
Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop. However, modern advanced user models, often designed…
Distributed Influence-Augmented Local Simulators for Parallel MARL in Large Networked Systems
Miguel Suau, Jinke He, Mustafa Mert Çelikok +2
Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning. Many real-world problems, however, exhibit overly…