Cover Image

Improving Policy Optimization via $\varepsilon$-Retrain

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Marzari, Luca, Donti, Priya L., Liu, Changliu, Marchesini, Enrico
Format:	Preprint
Published:	2024
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees
by: Marzari, Luca, et al.
Published: (2023)

Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learning
by: Marzari, Luca, et al.
Published: (2026)

RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations
by: Marchesini, Enrico, et al.
Published: (2025)

Revisiting the Initial Steps in Adaptive Gradient Descent Optimization
by: Abuduweili, Abulikemu, et al.
Published: (2024)

Absolute Policy Optimization
by: Zhao, Weiye, et al.
Published: (2023)

Improving Feasibility via Fast Autoencoder-Based Projections
by: Chzhen, Maria, et al.
Published: (2026)

Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation
by: Marzari, Luca, et al.
Published: (2025)

Estimating Neural Network Robustness via Lipschitz Constant and Architecture Sensitivity
by: Abuduweili, Abulikemu, et al.
Published: (2024)

Probabilistically Tightened Linear Relaxation-based Perturbation Analysis for Neural Network Verification
by: Marzari, Luca, et al.
Published: (2025)

FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees
by: Nguyen, Hoang T., et al.
Published: (2025)

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations
by: Marzari, Luca, et al.
Published: (2024)

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds
by: Marzari, Luca, et al.
Published: (2025)

RobustX: Robust Counterfactual Explanations Made Easy
by: Jiang, Junqi, et al.
Published: (2025)

Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment
by: Peng, Fred Zhangzhi, et al.
Published: (2026)

When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning
by: Hossain, Elias, et al.
Published: (2026)

Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
by: Zhao, Weiye, et al.
Published: (2024)

PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs
by: Zimmer, Max, et al.
Published: (2023)

Application-Driven Innovation in Machine Learning
by: Rolnick, David, et al.
Published: (2024)

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization
by: Feng, Xiaohua, et al.
Published: (2024)

Complexity-Regularized Proximal Policy Optimization
by: Serfilippi, Luca, et al.
Published: (2025)

Assessing Per-Sample Membership Inference Vulnerability without Retraining
by: Dorseuil, Valentin, et al.
Published: (2026)

Sustainable Machine Learning Retraining: Optimizing Energy Efficiency Without Compromising Accuracy
by: Poenaru-Olaru, Lorena, et al.
Published: (2025)

A Free Lunch in LLM Compression: Revisiting Retraining after Pruning
by: Wagner, Moritz, et al.
Published: (2025)

Spectral Unforgetting: Post-Hoc Recovery of Damaged Capabilities Without Retraining
by: Abro, Aarash, et al.
Published: (2026)

Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences
by: Bertsimas, Dimitris, et al.
Published: (2024)

Estimating the Effects of Sample Training Orders for Large Language Models without Retraining
by: Yang, Hao, et al.
Published: (2025)

Is Retraining-Free Enough? The Necessity of Router Calibration for Efficient MoE Compression
by: Hyeon, Sieun, et al.
Published: (2026)

Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
by: Zeng, Qingyuan, et al.
Published: (2026)

On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization
by: Shankar, Kaaustaaub, et al.
Published: (2025)

Pruning Foundation Models for High Accuracy without Retraining
by: Zhao, Pu, et al.
Published: (2024)

Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning
by: Li, Xuan, et al.
Published: (2026)

Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining
by: Han, Bing, et al.
Published: (2025)

Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
by: Liu, Zeyuan, et al.
Published: (2026)

Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
by: Zhang, Xiaoying, et al.
Published: (2024)

Fast Explanations via Policy Gradient-Optimized Explainer
by: Pan, Deng, et al.
Published: (2024)

Bootstrapping LLMs via Preference-Based Policy Optimization
by: Jia, Chen
Published: (2025)

Value-Free Policy Optimization via Reward Partitioning
by: Faye, Bilal, et al.
Published: (2025)

Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization
by: Liu, Zongkai, et al.
Published: (2024)

Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retraining with Pluralistic Preferences
by: Falahati, Ali, et al.
Published: (2026)

Decision Flow Policy Optimization
by: Hu, Jifeng, et al.
Published: (2025)