No article text was recorded for this version.
reference-advantage decomposition
Version 1 of 118 papers22 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Almost Optimal Model-Free Reinforcement Learningvia Reference-Advantage Decomposition
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
- Blog: Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
- Blog: Off-Policy Reinforcement Learning with Delayed Rewards
- Blog: The Efficacy of Pessimism in Asynchronous Q-Learning
- Blog: Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time
- Blog: Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning
- Blog: Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning
- Blog: Direct Advantage Estimation
- Blog: Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity
- Blog: Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
- Blog: When are Offline Two-Player Zero-Sum Markov Games Solvable?
- Blog: Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
- Blog: Learning and Testing Variable Partitions
- Blog: Federated $Q$-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
- Blog: Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
- Blog: Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity
History & citation
Current · Permanent link
- This direction split from function approximation scalability (56% overlap)
- This direction split from Reference Advantage Decomposition for Optimal Model Free Reinforcement Learning (83% overlap)
- This direction split from memory-efficient reinforcement learning (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_reference_advantage_decomposition_66f15b55,
title = {reference-advantage decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reference-advantage-decomposition/rdr_66f15b55ed2d4c27babefebe7931d08f},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_reference_advantage_decomposition_66f15b55_v1,
title = {reference-advantage decomposition},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reference-advantage-decomposition/rdr_66f15b55ed2d4c27babefebe7931d08f/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}