7 citations · 20 across the 27 of their papers we have counts for
28 papers
ALDER: Discovering the Laws of a World by Acting in It
Teng Cao, Yu Deng, Quentin Delfosse +1
Reliable world models should not only predict future states but express how actions change the world in an explicit, transparent and testable form, such as equations. Yet methods t…
Learning Explicit Behavioral Models with Adaptive Questions and World-Model Probes
Hikaru Shindo, Yu Deng, Teng Cao +5
Interactive agents trained only against task return can achieve high scores while failing to represent the mechanisms that make their actions succeed. This makes brittle behavior d…
Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
Teng Cao, Yu Deng, Hikaru Shindo +6
Modern embodied agents achieve impressive performance, but their task knowledge is often stored in neural weights, latent state, or prompt-bound memory, making individual policy kn…
GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
Hikaru Shindo, Henri Rößler, Quentin Delfosse +1
Neuro-symbolic Reinforcement Learning (NeSy-RL) combines symbolic reasoning with gradient-based optimization to achieve interpretable and generalizable policies. Relational concept…
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
Lukas Helff, Quentin Delfosse, David Steinmann +6
As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…
Boosting deep Reinforcement Learning using pretraining with Logical Options
Zihan Ye, Phil Chau, Raban Emunds +5
Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encodin…
Reasoning models do not yet follow their reasoning in autonomous driving: The KITScenes LongTail Dataset
Royden Wagner, Omer Sahin Tas, Jaime Villa +20
Handling rare events is the central open challenge in autonomous driving. Reasoning models, which generate explicit chains of reasoning before acting, promise to generalize to such…
STORM: Segment, Track, and Object Re-Localization from a Single Image
Yu Deng, Teng Cao, Hikaru Shindo +3
Accurate 6D pose estimation and tracking are core capabilities for physical AI systems, yet real-world deployment remains brittle and labor-intensive. Many pipelines rely on CAD mo…
Deep Reinforcement Learning Agents are not even close to Human Intelligence
Quentin Delfosse, Jannis Blüml, Fabian Tatai +6
Deep reinforcement learning (RL) agents achieve impressive results in a wide variety of tasks, but they lack zero-shot adaptation capabilities. While most robustness evaluations fo…
Better Decisions through the Right Causal World Model
Elisabeth Dillies, Quentin Delfosse, Jannis Blüml +3
Reinforcement learning (RL) agents have shown remarkable performances in various environments, where they can discover effective policies directly from sensory inputs. However, the…
Deep Reinforcement Learning via Object-Centric Attention
Jannis Blüml, Cedric Derstroff, Bjarne Gregori +3
Deep reinforcement learning agents, trained on raw pixel inputs, often fail to generalize beyond their training environments, relying on spurious correlations and irrelevant backgr…
Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
Hector Kohler, Quentin Delfosse, Waris Radji +2
There exist applications of reinforcement learning like medicine where policies need to be ''interpretable'' by humans. User studies have shown that some policy classes might be mo…
Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
Nils Grandien, Quentin Delfosse, Kristian Kersting
Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, t…
BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
Hikaru Shindo, Quentin Delfosse, Devendra Singh Dhami +1
Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural network…
OCALM: Object-Centric Assessment with Language Models
Timo Kaufmann, Jannis Blüml, Antonia Wüst +3
Properly defining a reward signal to efficiently train a reinforcement learning (RL) agent is a challenging task. Designing balanced objective functions from which a desired behavi…
EXPIL: Explanatory Predicate Invention for Learning in Games
Jingyuan Sha, Hikaru Shindo, Quentin Delfosse +2
Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders o…
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Quentin Delfosse, Jannis Blüml, Bjarne Gregori +1
Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means…
Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
Hector Kohler, Quentin Delfosse, Riad Akrour +2
Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust…
Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop
Hector Kohler, Quentin Delfosse, Paul Festor +1
Embracing the pursuit of intrinsically explainable reinforcement learning raises crucial questions: what distinguishes explainability from interpretability? Should explainable and…
Pix2Code: Learning to Compose Neural Visual Concepts as Programs
Antonia Wüst, Wolfgang Stammer, Quentin Delfosse +2
The challenge in learning abstract concepts from images in an unsupervised fashion lies in the required integration of visual perception and generalizable relational reasoning. Mor…
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Quentin Delfosse, Sebastian Sztwiertnia, Mark Rothermel +2
Goal misalignment, reward sparsity and difficult credit assignment are only a few of the many issues that make it difficult for deep reinforcement learning (RL) agents to learn opt…
OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
Quentin Delfosse, Jannis Blüml, Bjarne Gregori +2
Cognitive science and psychology suggest that object-centric representations of complex scenes are a promising step towards enabling efficient abstract reasoning from low-level per…
Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
Quentin Delfosse, Hikaru Shindo, Devendra Dhami +1
The limited priors required by neural networks make them the dominating choice to encode and learn policies using reinforcement learning (RL). However, they are also black-boxes, m…
Boosting Object Representation Learning via Motion and Object Continuity
Quentin Delfosse, Wolfgang Stammer, Thomas Rothenbacher +2
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they ma…