Copertina

Generalized Policy Improvement Algorithms with Theoretically Supported Sample Reuse

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Queeney, James, Paschalidis, Ioannis Ch., Cassandras, Christos G.
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees
di: Queeney, James, et al.
Pubblicazione: (2023)

Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees
di: Chen, Yilei, et al.
Pubblicazione: (2024)

Adversarial Imitation Learning from Visual Observations using Latent Information
di: Giammarino, Vittorio, et al.
Pubblicazione: (2023)

Multiple-policy Evaluation via Density Estimation
di: Chen, Yilei, et al.
Pubblicazione: (2024)

Distributionally Robust Token Optimization in RLHF
di: Jin, Yeping, et al.
Pubblicazione: (2026)

Visually Robust Adversarial Imitation Learning from Videos with Contrastive Learning
di: Giammarino, Vittorio, et al.
Pubblicazione: (2024)

A Model-Based Approach for Improving Reinforcement Learning Efficiency Leveraging Expert Observations
di: Ozcan, Erhan Can, et al.
Pubblicazione: (2024)

Reinforcement Learning-based Receding Horizon Control using Adaptive Control Barrier Functions for Safety-Critical Systems
di: Sabouni, Ehsan, et al.
Pubblicazione: (2024)

Theoretical Convergence of SMOTE-Generated Samples
di: Kamalov, Firuz, et al.
Pubblicazione: (2026)

GRAM: Generalization in Deep RL with a Robust Adaptation Module
di: Queeney, James, et al.
Pubblicazione: (2024)

Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning
di: Pravetz, Thomas
Pubblicazione: (2026)

When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR
di: Miao, Yuchun, et al.
Pubblicazione: (2026)

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
di: Jin, Yang, et al.
Pubblicazione: (2025)

Vision-Language Model Dialog Games for Self-Improvement
di: Konyushkova, Ksenia, et al.
Pubblicazione: (2025)

Method-Based Reasoning for Large Language Models: Extraction, Reuse, and Continuous Improvement
di: Su, Hong
Pubblicazione: (2025)

One-Shot Averaging for Distributed TD($λ$) Under Markov Sampling
di: Tian, Haoxing, et al.
Pubblicazione: (2024)

Geometric Re-Analysis of Classical MDP Solving Algorithms
di: Mustafin, Arsenii, et al.
Pubblicazione: (2025)

Provable and Practical In-Context Policy Optimization for Self-Improvement
di: Yu, Tianrun, et al.
Pubblicazione: (2026)

Blending Imitation and Reinforcement Learning for Robust Policy Improvement
di: Liu, Xuefeng, et al.
Pubblicazione: (2023)

Improved Sample Complexity Analysis of Natural Policy Gradient Algorithm with General Parameterization for Infinite Horizon Discounted Reward Markov Decision Processes
di: Mondal, Washim Uddin, et al.
Pubblicazione: (2023)

Deep SPI: Safe Policy Improvement via World Models
di: Delgrange, Florent, et al.
Pubblicazione: (2025)

Active Policy Improvement from Multiple Black-box Oracles
di: Liu, Xuefeng, et al.
Pubblicazione: (2023)

Going Beyond Heuristics by Imposing Policy Improvement as a Constraint
di: Lee, Chi-Chang, et al.
Pubblicazione: (2025)

Transformers Provably Implement In-Context Reinforcement Learning with Policy Improvement
di: Liang, Haodong, et al.
Pubblicazione: (2026)

Simulus: Combining Improvements in Sample-Efficient World Model Agents
di: Cohen, Lior, et al.
Pubblicazione: (2025)

On the Generalization Capability of Temporal Graph Learning Algorithms: Theoretical Insights and a Simpler Method
di: Cong, Weilin, et al.
Pubblicazione: (2024)

Accelerating Reinforcement Learning Algorithms Convergence using Pre-trained Large Language Models as Tutors With Advice Reusing
di: Toral, Lukas, et al.
Pubblicazione: (2025)

Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
di: Ahmad, H. M. Sabbir, et al.
Pubblicazione: (2025)

Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
di: Thrampoulidis, Christos, et al.
Pubblicazione: (2025)

Skill Reuse as Compression in Agentic RL
di: Xu, Zhikun, et al.
Pubblicazione: (2026)

Self-Improvement as Coherence Optimization: A Theoretical Account
di: Qiu, Tianyi, et al.
Pubblicazione: (2026)

Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
di: Zhang, Jinouwen, et al.
Pubblicazione: (2024)

Reward Weighted Classifier-Free Guidance as Policy Improvement in Autoregressive Models
di: Peysakhovich, Alexander, et al.
Pubblicazione: (2026)

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
di: Gui, Shurui, et al.
Pubblicazione: (2024)

Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap
di: Sun, Yifan, et al.
Pubblicazione: (2025)

Closing the gap between SVRG and TD-SVRG with Gradient Splitting
di: Mustafin, Arsenii, et al.
Pubblicazione: (2022)

On Value Iteration Convergence in Connected MDPs
di: Mustafin, Arsenii, et al.
Pubblicazione: (2024)

SIME: Enhancing Policy Self-Improvement with Modal-level Exploration
di: Jin, Yang, et al.
Pubblicazione: (2025)

Policy Improvement using Language Feedback Models
di: Zhong, Victor, et al.
Pubblicazione: (2024)

Neural Predictive Control to Coordinate Discrete- and Continuous-Time Models for Time-Series Analysis with Control-Theoretical Improvements
di: Li, Haoran, et al.
Pubblicazione: (2025)