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
1,984 results for “area:"reinforcement learning"” in ICLR 2027. 387 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]UMCTS-GRPO: Uncertainty-Aware Monte Carlo Tree Search for LLM Agent Reinforcement Learning▼1.2k1.67
[PDF]Neuron Sharing in Multi-Task Reinforcement Learning Policies Follows the Geometry of the Task Parameterization▼1361.33
[PDF]Count the constraints, not the tests: verifier diversity governs reinforcement learning from execution feedback▼1.3k1.75
[PDF]Rank Collapse Is Recoverable, Growing Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic▼1.2k1.67
[PDF]Freeze, Don't Clone: Fine-Tuning with Expressive Policies Without Retaining Offline Data▲3.9k1.67
[PDF]Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps▲6.1k2.00
[PDF]Do We Need Cost Critics? Local Cost Relabeling for Offline Safe Reinforcement Learning▼5.8k2.33
[PDF]AdvG: A Provably Convergent Actor–Critic Algorithm for Reinforcement Learning in Continuous Time and Space▲5103.00
[PDF]Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models▲143.33
[PDF]Analysis of MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible error▲3952.67
[PDF]Half the Rollouts, No Measurable Cost: A Seeded Audit of Dynamic Sampling and Credit Assignment in DAPO▼1.2k1.67
[PDF]Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving▲5.4k3.00
[PDF]When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO▲14k3.00
[PDF]Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay▼1361.33
Withdrawn or desk rejected (387)
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Recoverable Coordination Distillation for Decentralized Multi-Agent Reinforcement LearningWithdrawn1.67
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67