Cover Image

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Skalse, Joar, Abate, Alessandro
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Partial Identifiability in Inverse Reinforcement Learning For Agents With Non-Exponential Discounting
by: Skalse, Joar, et al.
Published: (2024)

On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks
by: Skalse, Joar, et al.
Published: (2024)

STARC: A General Framework For Quantifying Differences Between Reward Functions
by: Skalse, Joar, et al.
Published: (2023)

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
by: Fluri, Lukas, et al.
Published: (2024)

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning
by: Subramani, Rohan, et al.
Published: (2023)

Walking the Values in Bayesian Inverse Reinforcement Learning
by: Bajgar, Ondrej, et al.
Published: (2024)

Defining and Characterizing Reward Hacking
by: Skalse, Joar, et al.
Published: (2022)

On the Model-Misspecification in Reinforcement Learning
by: Li, Yunfan, et al.
Published: (2023)

PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning
by: Bajgar, Ondrej, et al.
Published: (2025)

Quantifying Potential Observation Missingness in Inverse Reinforcement Learning
by: Benac, Leo, et al.
Published: (2026)

Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
by: Melo, Luckeciano C., et al.
Published: (2025)

Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
by: Schnitzer, Yannik, et al.
Published: (2026)

DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL
by: Jackermeier, Mathias, et al.
Published: (2024)

Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
by: Audiffren, Julien, et al.
Published: (2026)

Robust Parameter Learning for Uncertain MDPs
by: Schnitzer, Yannik, et al.
Published: (2026)

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

Bisimulation Learning
by: Abate, Alessandro, et al.
Published: (2024)

Universal Batch Learning Under The Misspecification Setting
by: Vituri, Shlomi, et al.
Published: (2024)

Neural Proofs for Sound Verification and Control of Complex Systems
by: Abate, Alessandro
Published: (2025)

Inverse Reinforcement Learning without Reinforcement Learning
by: Swamy, Gokul, et al.
Published: (2023)

TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
by: Sestini, Alessandro, et al.
Published: (2025)

Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions
by: Abate, Alessandro, et al.
Published: (2026)

Distributional Inverse Reinforcement Learning
by: Wu, Feiyang, et al.
Published: (2025)

Temporal-Difference Variational Continual Learning
by: Melo, Luckeciano C., et al.
Published: (2024)

PlatoLTL: Learning to Generalize Across Symbols in LTL Instructions for Multi-Task RL
by: Cloete, Jacques, et al.
Published: (2026)

Robust Shielding for Safe Reinforcement Learning
by: Court, Edwin Hamel-De le, et al.
Published: (2026)

Efficient Imitation under Misspecification
by: Espinosa-Dice, Nicolas, et al.
Published: (2025)

SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL
by: Cloete, Jacques, et al.
Published: (2025)

Towards Generalized Inverse Reinforcement Learning
by: Dong, Chaosheng, et al.
Published: (2024)

The Virtues of Pessimism in Inverse Reinforcement Learning
by: Wu, David, et al.
Published: (2024)

Priors Matter: Addressing Misspecification in Bayesian Deep Q-Learning
by: van der Vaart, Pascal R., et al.
Published: (2025)

Jailbreaking as a Reward Misspecification Problem
by: Xie, Zhihui, et al.
Published: (2024)

Dissecting the Impact of Model Misspecification in Data-driven Optimization
by: Elmachtoub, Adam N., et al.
Published: (2025)

No-Regret Linear Bandits under Gap-Adjusted Misspecification
by: Liu, Chong, et al.
Published: (2025)

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

Inverse Reinforcement Learning with Multiple Planning Horizons
by: Yao, Jiayu, et al.
Published: (2024)

Accelerating Inverse Reinforcement Learning with Expert Bootstrapping
by: Wu, David, et al.
Published: (2024)

Confidence Aware Inverse Constrained Reinforcement Learning
by: Subramanian, Sriram Ganapathi, et al.
Published: (2024)

Vulnerability Analysis of Safe Reinforcement Learning via Inverse Constrained Reinforcement Learning
by: Fan, Jialiang, et al.
Published: (2026)