Cover Image

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhang, Xinyu
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence I.2.6; I.2.8
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites
by: Zhang, Qinshi, et al.
Published: (2026)

Working Paper: Active Causal Structure Learning with Latent Variables: Towards Learning to Detour in Autonomous Robots
by: Riscos, Pablo de los, et al.
Published: (2024)

AI and Machine Learning Approaches for Predicting Nanoparticles Toxicity The Critical Role of Physiochemical Properties
by: Yousaf, Iqra
Published: (2024)

On the Generalization Gap in LLM Planning: Tests and Verifier-Reward RL
by: Belcamino, Valerio, et al.
Published: (2026)

Safe Reinforcement Learning with Preference-based Constraint Inference
by: Li, Chenglin, et al.
Published: (2026)

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

CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning
by: Sauter, Andreas W. M., et al.
Published: (2024)

Regret-Aware Policy Optimization: Environment-Level Memory for Replay Suppression under Delayed Harm
by: Hiremath, Prakul Sunil
Published: (2026)

Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility
by: Oruganti, Venkatakrishna Reddy
Published: (2026)

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control
by: Hiremath, Prakul Sunil
Published: (2026)

Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems
by: Nuzhin, Egor E., et al.
Published: (2024)

SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library
by: Mishra, Satyam, et al.
Published: (2025)

FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data
by: Pivezhandi, Mohammad, et al.
Published: (2024)

On the Limits of Learned Importance Scoring for KV Cache Compression
by: Steele, Brady
Published: (2026)

Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds
by: Sasso, Remo, et al.
Published: (2025)

Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance
by: Silue, Bram, et al.
Published: (2025)

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks
by: Vincze, Mátyás, et al.
Published: (2024)

Not All Transitions Matter: Evidence from PPO
by: Basnet, Ajhesh
Published: (2026)

Embedded Safety-Aligned Intelligence via Differentiable Internal Alignment Embeddings
by: Rathva, Harsh, et al.
Published: (2025)

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
by: Zawalski, Michał, et al.
Published: (2022)

Incentives for Responsiveness, Instrumental Control and Impact
by: Carey, Ryan, et al.
Published: (2020)

Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery
by: Kang, Jiyeon, et al.
Published: (2025)

Learning to Select Goals in Automated Planning with Deep-Q Learning
by: Núñez-Molina, Carlos, et al.
Published: (2024)

A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control
by: Wang, Yuxuan, et al.
Published: (2025)

Social Interpretable Reinforcement Learning
by: Custode, Leonardo Lucio, et al.
Published: (2024)

Sketch Decompositions for Classical Planning via Deep Reinforcement Learning
by: Aichmüller, Michael, et al.
Published: (2024)

The Shortcomings of Force-from-Motion in Robot Learning
by: Aljalbout, Elie, et al.
Published: (2024)

Scaling Trends for Multi-Hop Contextual Reasoning in Mid-Scale Language Models
by: Steele, Brady, et al.
Published: (2026)

NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems
by: Núñez-Molina, Carlos, et al.
Published: (2023)

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning
by: Wang, Zizhao, et al.
Published: (2024)

MathLedger: A Verifiable Learning Substrate with Ledger-Attested Feedback
by: Abdullah, Ismail Ahmad
Published: (2025)

Fractional Policy Gradients: Reinforcement Learning with Long-Term Memory
by: Pawar, Urvi, et al.
Published: (2025)

Combining Trained Models in Reinforcement Learning
by: Patil, Ujjwal, et al.
Published: (2026)

From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning
by: Tomashevskiy, Timofey
Published: (2026)

Zero-Shot Context Generalization in Reinforcement Learning from Few Training Contexts
by: Chapman, James, et al.
Published: (2025)

Learning, Fast and Slow: Towards LLMs That Adapt Continually
by: Tiwari, Rishabh, et al.
Published: (2026)

From Next Token Prediction to (STRIPS) World Models
by: Núñez-Molina, Carlos, et al.
Published: (2025)

SCULPT: Constraint-Guided Pruned MCTS that Carves Efficient Paths for Mathematical Reasoning
by: Fang, Qitong, et al.
Published: (2026)

The ARC of Progress towards AGI: A Living Survey of Abstraction and Reasoning
by: Vahdati, Sahar, et al.
Published: (2026)

LakeMLB: Data Lake Machine Learning Benchmark
by: Pan, Feiyu, et al.
Published: (2026)