{"total":18,"rows":[{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"area":null},{"id":"2301.13442","title":"Scaling laws for single-agent reinforcement learning","created":"2023-01-31","cited_by_count":41,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36,"area":null},{"id":"2210.05064","title":"VER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement","created":"2022-10-11","cited_by_count":18,"area":null},{"id":"2512.06547","title":"A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation","created":"2025-12-06","cited_by_count":12,"area":null},{"id":"2410.05838","title":"Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit","created":"2024-10-08","cited_by_count":9,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2411.00999","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","created":"2024-11-01","cited_by_count":7,"area":null},{"id":"2604.07853","title":"QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training--Inference Mismatch","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2402.18824","title":"Batch size invariant Adam","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2603.06009","title":"Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2211.16566","title":"Relative Sparsity for Medical Decision Problems","created":"2022-11-29","cited_by_count":2,"area":null},{"id":"2608.29296","title":"When Do Larger Batches Help Scale LLM Reinforcement Learning?","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2609.39749","title":"Validity-Preserving Hierarchical RL for Joint Routing and Switch Placement in EDA","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.08975","title":"The Best Optimizer Depends on Batch Size","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.18853","title":"Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}