Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

Authors: Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This paper provides the first comprehensive analysis of this problem in online RL with general function approximation. We develop a provably sample-efficient algorithm achieving e O(Ccov H3/ε2) sample complexity... Our results also characterize when outcome-based feedback is statistically separated from per-step rewards, revealing an unavoidable exponential separation for certain MDPs. Together, these results constitute a theoretical foundation for understanding the statistical properties of outcome-based reinforcement learning.
Researcher Affiliation Academia EMAIL Zeyu Jia EMAIL Alexander Rakhlin EMAIL Tengyang Xie EMAIL
Pseudocode Yes Algorithm 1 Outcome-Based Exploration with Optimism Algorithm 2 Outcome-Based Exploration with Optimism for Determinsitic MDP Algorithm 3 Outcome-Based Exploration for Preference-based RL
Open Source Code No Answer: [NA] Justification: This paper does not include experiments requiring code.
Open Datasets No Answer: [NA] Justification: This paper does not include experiments.
Dataset Splits No Answer: [NA] Justification: This paper does not include experiments.
Hardware Specification No Answer: [NA] Justification: The paper does not include experiments.
Software Dependencies No Answer: [NA] Justification: This paper does not include experiments.
Experiment Setup No Answer: [NA] Justification: This paper does not include experiments.