NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
25 results for “keyword:"proximal policy optimization"” in ICLR 2027. 8 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping▼4.5k2.67
[PDF]Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning▼1.2k1.67
[PDF]Revealing the Emergent Learning Mechanisms of Critic Models in PPO for LLM Reinforcement Learning▲4012.67
[PDF]ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning▲3.0k2.33
[PDF]Learning to Train Underwater Image Enhancers with Reinforcement-Guided Update Scheduling▼1601.50
[PDF]VLNAPO: Gradient-Guided Harness Engineering with Key-Token Supervision for Full-Game VLNA Policy Optimization in OpenRA▼1.2k1.67
[PDF]Trust Regions Sell, But Who's Buying? Generalized Power-Law Surrogates for Clipped and KL-Constrained Reinforcement Learning▲13k2.40
Withdrawn or desk rejected (8)
[PDF]Learning What to Share: Latent Representations for FedRL with Observation DistractorsDesk rejected1.67
[PDF]MAESTRO: An Efficient Hierarchical Reinforcement Learning for Branch-and-Cut OrchestrationWithdrawn1.67
[PDF]Emergent Tool Use in the Hide-and-Seek Environment via an Adaptive Auto-CurriculumWithdrawn1.33
[PDF]Do Hyper-Connections Transfer to Reinforcement Learning? Sphere-Constrained Mixing and the Geometry of Depth.Withdrawn1.33