No article text was recorded for this version.
reward variance filtering
Version 1 of 121 papers27 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization
- Blog: On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
- Blog: Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning
- Blog: RAGEN-2: Reasoning Collapse in Agentic RL
- Blog: PyVision-RL: Forging Open Agentic Vision Models via RL
- Blog: TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization
- Blog: DemoStart: Demonstration-Led Auto-Curriculum Applied to Sim-to-Real with Multi-Fingered Robots
- Blog: GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
- Blog: Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs
- Blog: VisualScore: Learning Holistic Visual Quality Scores via Multi-Task Reasoning
- Blog: Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
- Blog: Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding
- Blog: MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM
- Blog: DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning
- Blog: OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment
- Blog: Group Critical-token Policy Optimization for Autoregressive Image Generation
- Blog: Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- Blog: Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
- Blog: CofactGVR: Counterfactual Intervention for Grounded Visual Reasoning
- Blog: Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
- Blog: TreeRPO: Tree Relative Policy Optimization
History & citation
Current · Permanent link
- This direction split from Dynamic Reward Variance Filtering for Stable Policy Optimization (57% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_reward_variance_filtering_e8048a8b,
title = {reward variance filtering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-variance-filtering/rdr_e8048a8b22b246f28788a534b2f62f2c},
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_reward_variance_filtering_e8048a8b_v1,
title = {reward variance filtering},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/reward-variance-filtering/rdr_e8048a8b22b246f28788a534b2f62f2c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}