Copertina

Reducing Reward Dependence in RL Through Adaptive Confidence Discounting

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Satici, Muhammed Yusuf, Roberts, David L.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Autonomous Curriculum Design via Relative Entropy Based Task Modifications
di: Satici, Muhammed Yusuf, et al.
Pubblicazione: (2025)

Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor
di: Grand-Clément, Julien, et al.
Pubblicazione: (2023)

Discounted Adaptive Online Learning: Towards Better Regularization
di: Zhang, Zhiyu, et al.
Pubblicazione: (2024)

Action-Dependent Optimality-Preserving Reward Shaping
di: Forbes, Grant C., et al.
Pubblicazione: (2025)

Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning
di: Yin, Shuyu, et al.
Pubblicazione: (2024)

Revisiting Value Iteration: Unified Analysis of Discounted and Average-Reward Cases
di: Mustafin, Arsenii, et al.
Pubblicazione: (2025)

Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs
di: Hong, Kihyuk, et al.
Pubblicazione: (2024)

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking
di: Singha, Disha
Pubblicazione: (2026)

The Impact of Post-training on Data Contamination
di: Kocyigit, Muhammed Yusuf, et al.
Pubblicazione: (2026)

Adaptive Discounting of Training Time Attacks
di: Bector, Ridhima, et al.
Pubblicazione: (2024)

Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitioners
di: Muslimani, Calarina, et al.
Pubblicazione: (2025)

AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning
di: Wang, Yaomin, et al.
Pubblicazione: (2026)

Reward Compatibility: A Framework for Inverse RL
di: Lazzati, Filippo, et al.
Pubblicazione: (2025)

The Plug-in Approach for Average-Reward and Discounted MDPs: Optimal Sample Complexity Analysis
di: Zurek, Matthew, et al.
Pubblicazione: (2024)

On-Policy RL with Optimal Reward Baseline
di: Hao, Yaru, et al.
Pubblicazione: (2025)

Online Recommendations for Agents with Discounted Adaptive Preferences
di: Agarwal, Arpit, et al.
Pubblicazione: (2023)

Natural Policy Gradient for Average Reward Non-Stationary RL
di: Jali, Neharika, et al.
Pubblicazione: (2025)

Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting
di: Feng, Yunzhen, et al.
Pubblicazione: (2025)

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
di: Cai, Xin-Qiang, et al.
Pubblicazione: (2026)

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs
di: Thoppe, Gugan, et al.
Pubblicazione: (2026)

Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
di: Tomihari, Akiyoshi, et al.
Pubblicazione: (2026)

RL + Transformer = A General-Purpose Problem Solver
di: Rentschler, Micah, et al.
Pubblicazione: (2025)

Diagnosing and Mitigating System Bias in Self-Rewarding RL
di: Tan, Chuyi, et al.
Pubblicazione: (2025)

Gatekeeper: Improving Model Cascades Through Confidence Tuning
di: Rabanser, Stephan, et al.
Pubblicazione: (2025)

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits
di: Cheng, Tianhao, et al.
Pubblicazione: (2026)

Less is more? Rewards in RL for Cyber Defence
di: Bates, Elizabeth, et al.
Pubblicazione: (2025)

Learning to Reason Efficiently with Discounted Reinforcement Learning
di: Ayoub, Alex, et al.
Pubblicazione: (2025)

Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS
di: Jin, Can, et al.
Pubblicazione: (2025)

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
di: Mukherjee, Subhojyoti, et al.
Pubblicazione: (2025)

General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies
di: Wang, Jianxun, et al.
Pubblicazione: (2026)

ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs
di: Zhang, Bonan, et al.
Pubblicazione: (2025)

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
di: Kim, Kyuyoung, et al.
Pubblicazione: (2024)

Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training
di: Salimi, Moein, et al.
Pubblicazione: (2026)

Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL
di: Ghosh, Udita, et al.
Pubblicazione: (2026)

Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
di: Mahankali, Arvind, et al.
Pubblicazione: (2026)

Efficiently Solving Discounted MDPs with Predictions on Transition Matrices
di: Lyu, Lixing, et al.
Pubblicazione: (2025)

Bridging the Gap Between Average and Discounted TD Learning
di: Tian, Haoxing, et al.
Pubblicazione: (2026)

Online Linear Regression in Dynamic Environments via Discounting
di: Jacobsen, Andrew, et al.
Pubblicazione: (2024)

When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production Systems
di: Casey, Emma, et al.
Pubblicazione: (2026)

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)