Copertina

Getting By Goal Misgeneralization With a Little Help From a Mentor

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Trinh, Tu, Danesh, Mohamad H., Khanh, Nguyen X., Plaut, Benjamin
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
di: Plaut, Benjamin, et al.
Pubblicazione: (2024)

YRC-Bench: A Benchmark for Learning to Coordinate with Experts
di: Danesh, Mohamad H., et al.
Pubblicazione: (2025)

Avoiding Catastrophe in Online Learning by Asking for Help
di: Plaut, Benjamin, et al.
Pubblicazione: (2024)

Safe Learning Under Irreversible Dynamics via Asking for Help
di: Plaut, Benjamin, et al.
Pubblicazione: (2025)

Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards
di: Liaw, Sarah, et al.
Pubblicazione: (2025)

Safety Training Persists Through Helpfulness Optimization in LLM Agents
di: Plaut, Benjamin
Pubblicazione: (2026)

Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
di: Azran, Guy, et al.
Pubblicazione: (2023)

Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
di: Nguyen, Minh Duong, et al.
Pubblicazione: (2024)

Mitigating Goal Misgeneralization via Minimax Regret
di: Sadek, Karim Abdel, et al.
Pubblicazione: (2025)

Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions
di: Khorram, Saeed, et al.
Pubblicazione: (2024)

Drift Q-Learning
di: Houssaini, Anas, et al.
Pubblicazione: (2026)

Reinforcement Learning from LLM Feedback to Counteract Goal Misgeneralization
di: Barj, Houda Nait El, et al.
Pubblicazione: (2024)

ML-Driven Approaches to Combat Medicare Fraud: Advances in Class Imbalance Solutions, Feature Engineering, Adaptive Learning, and Business Impact
di: Farahmandazad, Dorsa, et al.
Pubblicazione: (2025)

Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning
di: Nguyen, Khanh, et al.
Pubblicazione: (2024)

Position: Capability Control Should be a Separate Goal From Alignment
di: Siddiqui, Shoaib Ahmed, et al.
Pubblicazione: (2026)

METIS: Mentoring Engine for Thoughtful Inquiry & Solutions
di: Kumar, Abhinav Rajeev, et al.
Pubblicazione: (2026)

SeqBattNet: A Discrete-State Physics-Informed Neural Network with Aging Adaptation for Battery Modeling
di: Tran, Khoa, et al.
Pubblicazione: (2025)

OGBench: Benchmarking Offline Goal-Conditioned RL
di: Park, Seohong, et al.
Pubblicazione: (2024)

Choice Between Partial Trajectories: Disentangling Goals from Beliefs
di: Marklund, Henrik, et al.
Pubblicazione: (2024)

Cross-Modality Controlled Molecule Generation with Diffusion Language Model
di: Zhang, Yunzhe, et al.
Pubblicazione: (2025)

Reconciling Spatial and Temporal Abstractions for Goal Representation
di: Zadem, Mehdi, et al.
Pubblicazione: (2024)

Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
di: Khanh, Truong Xuan
Pubblicazione: (2026)

Foundations of Artificial Intelligence Frameworks: Notion and Limits of AGI
di: Bui, Khanh Gia
Pubblicazione: (2025)

Accelerating Goal-Conditioned RL Algorithms and Research
di: Bortkiewicz, Michał, et al.
Pubblicazione: (2024)

Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
di: Nimonkar, Chirayu, et al.
Pubblicazione: (2025)

HyBattNet: Hybrid Framework for Predicting the Remaining Useful Life of Lithium-Ion Batteries
di: Tran, Khoa, et al.
Pubblicazione: (2025)

How Far Can Fairness Constraints Help Recover From Biased Data?
di: Sharma, Mohit, et al.
Pubblicazione: (2023)

Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning
di: Singh, Sagalpreet, et al.
Pubblicazione: (2025)

Mode-Dependent Rectification for Stable PPO Training
di: Mohamad, Mohamad, et al.
Pubblicazione: (2026)

HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback
di: Li, Ang, et al.
Pubblicazione: (2024)

Test-time Diverse Reasoning by Riemannian Activation Steering
di: Khanh, Ly Tran Ho, et al.
Pubblicazione: (2025)

HIQL: Offline Goal-Conditioned RL with Latent States as Actions
di: Park, Seohong, et al.
Pubblicazione: (2023)

Autonomous Learning From Success and Failure: Goal-Conditioned Supervised Learning with Negative Feedback
di: Zhang, Zeqiang, et al.
Pubblicazione: (2025)

Minimizing Collateral Damage in Activation Steering
di: Nguyen, Tam, et al.
Pubblicazione: (2026)

Measuring Goal-Directedness
di: MacDermott, Matt, et al.
Pubblicazione: (2024)

Dual Goal Representations
di: Park, Seohong, et al.
Pubblicazione: (2025)

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
di: Zheng, Chongyi, et al.
Pubblicazione: (2023)

Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning
di: Wu, Lisheng, et al.
Pubblicazione: (2024)

Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
di: Choi, Jinwoo, et al.
Pubblicazione: (2026)

Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning
di: Rens, Gavin B.
Pubblicazione: (2025)