Cover Image

Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Banerjee, Debangshu, Gopalan, Aditya
Format:	Preprint
Published:	2023
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards Reliable Alignment: Uncertainty-aware RLHF
by: Banerjee, Debangshu, et al.
Published: (2024)

Towards Reliable, Uncertainty-Aware Alignment
by: Banerjee, Debangshu, et al.
Published: (2025)

Why DPO is a Misspecified Estimator and How to Fix It
by: Gopalan, Aditya, et al.
Published: (2025)

On-line Learning in Tree MDPs by Treating Policies as Bandit Arms
by: Shah, Anvay, et al.
Published: (2026)

Data Shifts Hurt CoT: A Theoretical Study
by: Yin, Lang, et al.
Published: (2025)

Vertical Federated Learning in Practice: The Good, the Bad, and the Ugly
by: Wu, Zhaomin, et al.
Published: (2025)

Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning
by: Hoang, Huy, et al.
Published: (2023)

Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions
by: Mhammedi, Zakaria
Published: (2024)

Identifying All ε-Best Arms in (Misspecified) Linear Bandits
by: Li, Zhekai, et al.
Published: (2025)

When Bad Data Leads to Good Models
by: Li, Kenneth, et al.
Published: (2025)

Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
by: Bansal, Hritik, et al.
Published: (2024)

Ambient Diffusion Omni: Training Good Models with Bad Data
by: Daras, Giannis, et al.
Published: (2025)

Are Domain Generalization Benchmarks with Accuracy on the Line Misspecified?
by: Salaudeen, Olawale, et al.
Published: (2025)

FADE: Why Bad Descriptions Happen to Good Features
by: Puri, Bruno, et al.
Published: (2025)

No-Regret Reinforcement Learning in Smooth MDPs
by: Maran, Davide, et al.
Published: (2024)

Conservative Contextual Bandits: Beyond Linear Representations
by: Deb, Rohan, et al.
Published: (2024)

Efficient Solution and Learning of Robust Factored MDPs
by: Schnitzer, Yannik, et al.
Published: (2025)

Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error
by: Du, Ally Yalei, et al.
Published: (2024)

The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
by: Yi, Huiyang, et al.
Published: (2025)

When Good Equations Get Bad Scores: Improving Symbolic Regression Through Better Parameter Optimization
by: Wang, Boxiao, et al.
Published: (2026)

Simulation, Modelling and Classification of Wiki Contributors: Spotting The Good, The Bad, and The Ugly
by: Méndez, Silvia García, et al.
Published: (2024)

The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification
by: Baharav, Tavor Z., et al.
Published: (2025)

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks
by: Ge, Luise, et al.
Published: (2025)

AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
by: Mazumder, Aritra, et al.
Published: (2026)

Transitive RL: Value Learning via Divide and Conquer
by: Park, Seohong, et al.
Published: (2025)

Prospect-Theory Behavior from Bellman Optimality in MDPs with Catastrophic States
by: Chen, Yujiao
Published: (2026)

Predicting Bad Goods Risk Scores with ARIMA Time Series: A Novel Risk Assessment Approach
by: Gond, Bishwajit Prasad
Published: (2025)

Quasimetric Value Functions with Dense Rewards
by: Valieva, Khadichabonu, et al.
Published: (2024)

DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
by: Shrestha, Aayam, et al.
Published: (2020)

Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs
by: Maran, Davide, et al.
Published: (2024)

Low-Rank MDPs with Continuous Action Spaces
by: Bennett, Andrew, et al.
Published: (2023)

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
by: Grillotti, Luca, et al.
Published: (2024)

CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios
by: Yi, Huiyang, et al.
Published: (2026)

Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs
by: Wendland, Joshua, et al.
Published: (2026)

Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
by: Shakerinava, Mehran, et al.
Published: (2025)

Geometry of Drifting MDPs with Path-Integral Stability Certificates
by: Zhang, Zuyuan, et al.
Published: (2026)

Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
by: Eshwar, S. R., et al.
Published: (2025)

Neural Active Learning Beyond Bandits
by: Ban, Yikun, et al.
Published: (2024)

Learning When to Trust in Contextual Bandits
by: Ghasemi, Majid, et al.
Published: (2026)

Efficient Adversarial Attacks on High-dimensional Offline Bandits
by: Hosseini, Seyed Mohammad Hadi, et al.
Published: (2026)