93 citations · 99 across the 9 of their papers we have counts for
5 papers · 1 filter
From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models
Christian Gumbsch, Leonardo Barcellona, Lennard Schünemann +7
Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics. Recent work has explored…
Causal Process Models: Reframing Dynamic Causal Graph Discovery as a Reinforcement Learning Problem
Turan Orujlu, Christian Gumbsch, Martin V. Butz +1
Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolv…
Developing hierarchical anticipations via neural network-based event segmentation
Christian Gumbsch, Maurits Adam, Birgit Elsner +2
Humans can make predictions on various time scales and hierarchical levels. Thereby, the learning of event encodings seems to play a crucial role. In this work we model the develop…
Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains
Christian Gumbsch, Martin V. Butz, Georg Martius
A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hi…
Latent Event-Predictive Encodings through Counterfactual Regularization
Dania Humaidan, Sebastian Otte, Christian Gumbsch +2
A critical challenge for any intelligent system is to infer structure from continuous data streams. Theories of event-predictive cognition suggest that the brain segments sensorimo…