Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sinha, Abhijeet, Elango, Sundari, Liu, Dianbo
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

How does My Model Fail? Automatic Identification and Interpretation of Physical Plausibility Failure Modes with Matryoshka Transcoders
di: Tang, Yiming, et al.
Pubblicazione: (2025)

Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms
di: Flageat, Manon, et al.
Pubblicazione: (2023)

Representation Collapsing Problems in Vector Quantization
di: Zhao, Wenhao, et al.
Pubblicazione: (2024)

Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return
di: Peng, Nianli, et al.
Pubblicazione: (2023)

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
di: Vetcha, Nitin, et al.
Pubblicazione: (2026)

Collapsing Sequence-Level Data-Policy Coverage via Poisoning Attack in Offline Reinforcement Learning
di: Zhou, Xue, et al.
Pubblicazione: (2025)

Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization
di: Zhao, Wenhao, et al.
Pubblicazione: (2026)

Meta-Learning Reinforcement Learning for Crypto-Return Prediction
di: Wang, Junqiao, et al.
Pubblicazione: (2025)

Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
di: Cheng, Ruoxi, et al.
Pubblicazione: (2025)

Discovery of False Data Injection Schemes on Frequency Controllers with Reinforcement Learning
di: Prasad, Romesh, et al.
Pubblicazione: (2024)

How to Provably Improve Return Conditioned Supervised Learning?
di: Liu, Zhishuai, et al.
Pubblicazione: (2025)

Hybrid Inverse Reinforcement Learning
di: Ren, Juntao, et al.
Pubblicazione: (2024)

Multi-Mode Process Control Using Multi-Task Inverse Reinforcement Learning
di: Lin, Runze, et al.
Pubblicazione: (2025)

In-Dataset Trajectory Return Regularization for Offline Preference-based Reinforcement Learning
di: Tu, Songjun, et al.
Pubblicazione: (2024)

PCGRL+: Scaling, Control and Generalization in Reinforcement Learning Level Generators
di: Earle, Sam, et al.
Pubblicazione: (2024)

Provably Efficient Exploration in Inverse Constrained Reinforcement Learning
di: Yue, Bo, et al.
Pubblicazione: (2024)

Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning
di: Wang, Ruhan, et al.
Pubblicazione: (2024)

Performance Asymmetry in Model-Based Reinforcement Learning
di: Lim, Jing Yu, et al.
Pubblicazione: (2025)

Fast Rates for Inverse Reinforcement Learning
di: Schlaginhaufen, Andreas, et al.
Pubblicazione: (2026)

On the Effective Horizon of Inverse Reinforcement Learning
di: Xu, Yiqing, et al.
Pubblicazione: (2023)

Environment Design for Inverse Reinforcement Learning
di: Buening, Thomas Kleine, et al.
Pubblicazione: (2022)

Recursive Deep Inverse Reinforcement Learning
di: Ghanem, Paul, et al.
Pubblicazione: (2025)

Inverse Reinforcement Learning With Constraint Recovery
di: Das, Nirjhar, et al.
Pubblicazione: (2023)

Evolution Guided Generative Flow Networks
di: Ikram, Zarif, et al.
Pubblicazione: (2024)

Deconstructing Generative Diversity: An Information Bottleneck Analysis of Discrete Latent Generative Models
di: Wu, Yudi, et al.
Pubblicazione: (2025)

STAS: Spatial-Temporal Return Decomposition for Multi-agent Reinforcement Learning
di: Chen, Sirui, et al.
Pubblicazione: (2023)

Invariant Learning via Probability of Sufficient and Necessary Causes
di: Yang, Mengyue, et al.
Pubblicazione: (2023)

Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
di: Wang, Jinping, et al.
Pubblicazione: (2026)

Partial Identifiability and Misspecification in Inverse Reinforcement Learning
di: Skalse, Joar, et al.
Pubblicazione: (2024)

Is Optimal Transport Necessary for Inverse Reinforcement Learning?
di: Dong, Zixuan, et al.
Pubblicazione: (2025)

Inverse Reinforcement Learning with Sub-optimal Experts
di: Poiani, Riccardo, et al.
Pubblicazione: (2024)

Kernel Density Bayesian Inverse Reinforcement Learning
di: Mandyam, Aishwarya, et al.
Pubblicazione: (2023)

Inverse Reinforcement Learning by Estimating Expertise of Demonstrators
di: Beliaev, Mark, et al.
Pubblicazione: (2024)

Towards Interpretable Deep Reinforcement Learning Models via Inverse Reinforcement Learning
di: Xie, Sean, et al.
Pubblicazione: (2022)

Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks
di: Gong, Yanxiang, et al.
Pubblicazione: (2022)

ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism
di: Elango, Venmugil
Pubblicazione: (2025)

A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges
di: Liu, Guiliang, et al.
Pubblicazione: (2024)

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
di: Zhao, Lei, et al.
Pubblicazione: (2023)

Inverse Reinforcement Learning from Non-Stationary Learning Agents
di: Sivakumar, Kavinayan P., et al.
Pubblicazione: (2024)

Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
di: Roth, Andreas, et al.
Pubblicazione: (2023)