Deep Reinforcement Learning Agents are not even close to Human Intelligence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Delfosse, Quentin, Blüml, Jannis, Tatai, Fabian, Vincent, Théo, Gregori, Bjarne, Dillies, Elisabeth, Peters, Jan, Rothkopf, Constantin, Kersting, Kristian
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Deep Reinforcement Learning via Object-Centric Attention
by: Blüml, Jannis, et al.
Published: (2025)

HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
by: Delfosse, Quentin, et al.
Published: (2024)

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
by: Delfosse, Quentin, et al.
Published: (2023)

Better Decisions through the Right Causal World Model
by: Dillies, Elisabeth, et al.
Published: (2025)

OCALM: Object-Centric Assessment with Language Models
by: Kaufmann, Timo, et al.
Published: (2024)

Boosting deep Reinforcement Learning using pretraining with Logical Options
by: Ye, Zihan, et al.
Published: (2026)

Interpretable end-to-end Neurosymbolic Reinforcement Learning agents
by: Grandien, Nils, et al.
Published: (2024)

Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
by: Cömer, Can, et al.
Published: (2025)

Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
by: Czech, Johannes, et al.
Published: (2023)

Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
by: Delfosse, Quentin, et al.
Published: (2024)

Adaptive Rational Activations to Boost Deep Reinforcement Learning
by: Delfosse, Quentin, et al.
Published: (2021)

GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning
by: Shindo, Hikaru, et al.
Published: (2026)

Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
by: Cao, Teng, et al.
Published: (2026)

Amplifying Exploration in Monte-Carlo Tree Search by Focusing on the Unknown
by: Derstroff, Cedric, et al.
Published: (2024)

Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
by: Helfenstein, Felix, et al.
Published: (2024)

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
by: Kohler, Hector, et al.
Published: (2024)

BlendRL: A Framework for Merging Symbolic and Neural Policy Learning
by: Shindo, Hikaru, et al.
Published: (2024)

Boosting Object Representation Learning via Motion and Object Continuity
by: Delfosse, Quentin, et al.
Published: (2022)

Fodor and Pylyshyn's Legacy: Still No Human-like Systematic Compositionality in Neural Networks
by: Woydt, Tim, et al.
Published: (2025)

EXPIL: Explanatory Predicate Invention for Learning in Games
by: Sha, Jingyuan, et al.
Published: (2024)

Pix2Code: Learning to Compose Neural Visual Concepts as Programs
by: Wüst, Antonia, et al.
Published: (2024)

Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
by: Vincent, Théo, et al.
Published: (2024)

STORM: Segment, Track, and Object Re-Localization from a Single Image
by: Deng, Yu, et al.
Published: (2025)

Primes as a Field on a Discrete Torus: Primorial Field Dynamics, Gap Composition Profiles, and an Information-Theoretic Reformulation -- PrimSpace v3.0
by: Tatai, László
Published: (2026)

Primes as a Field on a Discrete Torus
by: Tatai, László
Published: (2026)

Inverse decision-making using neural amortized Bayesian actors
by: Straub, Dominik, et al.
Published: (2024)

Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning
by: Ye, Zihan, et al.
Published: (2025)

Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
by: Wüst, Antonia, et al.
Published: (2024)

Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning
by: Vincent, Théo, et al.
Published: (2024)

Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning
by: Vincent, Théo, et al.
Published: (2025)

Learning Particle Dynamics Subject to Rigid Body Manipulations Using Graph Neural Networks
by: Midlagajni, Niteesh, et al.
Published: (2025)

On a closed-loop identification challenge in feedback optimization
by: Løvland, Kristian Lindbäck, et al.
Published: (2025)

Anchored Dyck Paths
by: Dillies, Jimmy
Published: (2026)

Human-Allied Relational Reinforcement Learning
by: Darvishvand, Fateme Golivand, et al.
Published: (2025)

Deep Classifier Mimicry without Data Access
by: Braun, Steven, et al.
Published: (2023)

Adaptable Hindsight Experience Replay for Search-Based Learning
by: Vazaios, Alexandros, et al.
Published: (2025)

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
by: Helff, Lukas, et al.
Published: (2026)

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop
by: Kohler, Hector, et al.
Published: (2024)

Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
by: Mitchell, Rupert, et al.
Published: (2025)

Evaluating Interpretable Reinforcement Learning by Distilling Policies into Programs
by: Kohler, Hector, et al.
Published: (2025)