Imagen de Portada

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Subramani, Rohan, Williams, Marcus, Heitmann, Max, Holm, Halfdan, Griffin, Charlie, Skalse, Joar
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
por: Skalse, Joar, et al.
Publicado: (2024)

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

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

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

Defining and Characterizing Reward Hacking
por: Skalse, Joar, et al.
Publicado: (2022)

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

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

Automating Formal Verification with Reinforcement Learning and Recursive Inference
por: Tan, Max
Publicado: (2026)

Password-Activated Shutdown Protocols for Misaligned Frontier Agents
por: Williams, Kai, et al.
Publicado: (2025)

Multi-objective Reinforcement learning from AI Feedback
por: Williams, Marcus
Publicado: (2024)

Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution
por: Munn, Humphrey, et al.
Publicado: (2025)

EXPO: Stable Reinforcement Learning with Expressive Policies
por: Dong, Perry, et al.
Publicado: (2025)

Balancing Expressivity and Robustness: Constrained Rational Activations for Reinforcement Learning
por: Surdej, Rafał, et al.
Publicado: (2025)

Towards Formalizing Reinforcement Learning Theory
por: Zhang, Shangtong
Publicado: (2025)

Polychromic Objectives for Reinforcement Learning
por: Hamid, Jubayer Ibn, et al.
Publicado: (2025)

Pareto Set Learning for Multi-Objective Reinforcement Learning
por: Liu, Erlong, et al.
Publicado: (2025)

Preference-based Multi-Objective Reinforcement Learning
por: Mu, Ni, et al.
Publicado: (2025)

Objective-Specific Privileged Bases via Full-Prefix Matryoshka Learning
por: Talukder, Arghamitra, et al.
Publicado: (2026)

Towards Provable Emergence of In-Context Reinforcement Learning
por: Wang, Jiuqi, et al.
Publicado: (2025)

Optimistic Reinforcement Learning with Quantile Objectives
por: Alipour-Vaezi, Mohammad, et al.
Publicado: (2025)

On Generalization Across Environments In Multi-Objective Reinforcement Learning
por: Teoh, Jayden, et al.
Publicado: (2025)

Expressive Value Learning for Scalable Offline Reinforcement Learning
por: Espinosa-Dice, Nicolas, et al.
Publicado: (2025)

Expressive Temporal Specifications for Reward Monitoring
por: Adalat, Omar, et al.
Publicado: (2025)

Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy
por: Doo, JaeHyeok, et al.
Publicado: (2026)

A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
por: Chen, Ying-Tu, et al.
Publicado: (2026)

Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning
por: Wang, Yudan, et al.
Publicado: (2024)

Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning
por: Park, Giseung, et al.
Publicado: (2025)

Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
por: Ganesh, Swetha, et al.
Publicado: (2026)

Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
por: Park, Giseung, et al.
Publicado: (2026)

Benchmarking Offline Multi-Objective Reinforcement Learning in Critical Care
por: Bansal, Aryaman, et al.
Publicado: (2025)

Multi-Objective Reinforcement Learning for Generating Covalent Inhibitor Candidates
por: Gil, Renee
Publicado: (2026)

Reinforcement Learning with $ω$-Regular Objectives and Constraints
por: Wagner, Dominik, et al.
Publicado: (2025)

Multi-Objective Reinforcement Learning for Water Management
por: Osika, Zuzanna, et al.
Publicado: (2025)

Demonstration Guided Multi-Objective Reinforcement Learning
por: Lu, Junlin, et al.
Publicado: (2024)

The Formalism-Implementation Gap in Reinforcement Learning Research
por: Castro, Pablo Samuel
Publicado: (2025)

Games for AI Control: Models of Safety Evaluations of AI Deployment Protocols
por: Griffin, Charlie, et al.
Publicado: (2024)

Effective Reward Specification in Deep Reinforcement Learning
por: Roy, Julien
Publicado: (2024)

Active Learning of Molecular Data for Task-Specific Objectives
por: Ghosh, Kunal, et al.
Publicado: (2024)

Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data
por: Deng, Shilong, et al.
Publicado: (2025)

Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought
por: Xie, Zixuan, et al.
Publicado: (2026)