Copertina

Bridging RL Theory and Practice with the Effective Horizon

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Laidlaw, Cassidy, Russell, Stuart, Dragan, Anca
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Effective Horizon Explains Deep RL Performance in Stochastic Environments
di: Laidlaw, Cassidy, et al.
Pubblicazione: (2023)

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking
di: Laidlaw, Cassidy, et al.
Pubblicazione: (2024)

AssistanceZero: Scalably Solving Assistance Games
di: Laidlaw, Cassidy, et al.
Pubblicazione: (2025)

AI Alignment with Changing and Influenceable Reward Functions
di: Carroll, Micah, et al.
Pubblicazione: (2024)

Benchmarking and Improving Monitors for Out-Of-Distribution Alignment Failure in LLMs
di: Feng, Dylan, et al.
Pubblicazione: (2026)

Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision
di: Ye, Yaowen, et al.
Pubblicazione: (2025)

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
di: Siththaranjan, Anand, et al.
Pubblicazione: (2023)

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
di: Lang, Leon, et al.
Pubblicazione: (2024)

A Generalized Acquisition Function for Preference-based Reward Learning
di: Ellis, Evan, et al.
Pubblicazione: (2024)

RL, but don't do anything I wouldn't do
di: Cohen, Michael K., et al.
Pubblicazione: (2024)

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
di: Hong, Joey, et al.
Pubblicazione: (2024)

Adversaries Can Misuse Combinations of Safe Models
di: Jones, Erik, et al.
Pubblicazione: (2024)

Interactive Dialogue Agents via Reinforcement Learning on Hindsight Regenerations
di: Hong, Joey, et al.
Pubblicazione: (2024)

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
di: Wu, Ian, et al.
Pubblicazione: (2026)

Horizon Reduction Makes RL Scalable
di: Park, Seohong, et al.
Pubblicazione: (2025)

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making
di: Myers, Vivek, et al.
Pubblicazione: (2024)

Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
di: Myers, Vivek, et al.
Pubblicazione: (2025)

Bridging Theory and Practice in Crafting Robust Spiking Reservoirs
di: Freddi, Ruggero, et al.
Pubblicazione: (2026)

Aligning Robot and Human Representations
di: Bobu, Andreea, et al.
Pubblicazione: (2023)

Training LLM Agents to Empower Humans
di: Ellis, Evan, et al.
Pubblicazione: (2025)

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
di: Williams, Marcus, et al.
Pubblicazione: (2024)

Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding
di: Xu, Jiamin, et al.
Pubblicazione: (2026)

Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL
di: Tao, Zhikun
Pubblicazione: (2025)

Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation
di: Pan, Michelle, et al.
Pubblicazione: (2024)

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
di: Li, Yunfei, et al.
Pubblicazione: (2025)

Bridging Theory and Practice in Link Representation with Graph Neural Networks
di: Lachi, Veronica, et al.
Pubblicazione: (2025)

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
di: Wang, Zhiyong, et al.
Pubblicazione: (2024)

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning
di: Zhu, Taojie, et al.
Pubblicazione: (2026)

The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
di: Li, Yingru, et al.
Pubblicazione: (2026)

An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines
di: Su, Jianhai, et al.
Pubblicazione: (2025)

Offline Imitation Learning by Controlling the Effective Planning Horizon
di: Ahn, Hee-Jun, et al.
Pubblicazione: (2024)

On the Effective Horizon of Inverse Reinforcement Learning
di: Xu, Yiqing, et al.
Pubblicazione: (2023)

Learning to Assist Humans without Inferring Rewards
di: Myers, Vivek, et al.
Pubblicazione: (2024)

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
di: Zhou, Runlin, et al.
Pubblicazione: (2025)

On Representation Complexity of Model-based and Model-free Reinforcement Learning
di: Zhu, Hanlin, et al.
Pubblicazione: (2023)

Effective Interplay between Sparsity and Quantization: From Theory to Practice
di: Harma, Simla Burcu, et al.
Pubblicazione: (2024)

Coalgebras for categorical deep learning: Representability and universal approximation
di: Mašulović, Dragan
Pubblicazione: (2026)

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

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

Randomness Helps Rigor: A Probabilistic Learning Rate Scheduler Bridging Theory and Deep Learning Practice
di: Devapriya, Dahlia, et al.
Pubblicazione: (2024)