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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sinha, Abhijeet, Elango, Sundari, Liu, Dianbo
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

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

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

Hybrid Inverse Reinforcement Learning
by: Ren, Juntao, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

Recursive Deep Inverse Reinforcement Learning
by: Ghanem, Paul, et al.
Published: (2025)

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

Evolution Guided Generative Flow Networks
by: Ikram, Zarif, et al.
Published: (2024)

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

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

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

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

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

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

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

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

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

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

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

ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism
by: Elango, Venmugil
Published: (2025)

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

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

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

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