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
48 results for “keyword:"safe reinforcement learning"” in ICLR 2027. 6 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Safe Executions Can Hide Policy Failure: A Proposal-Level Audit of Hybrid Control in Synthetic Interviews▲2.0k1.50
[PDF]Sanctuary: Safe Correlated Exploration for Online Vision-Language-Action Models Adaptation▼1361.33
[PDF]EpiPlan: Prospective Epigraph-Space Planning for Safe Multi-Agent Reinforcement Learning▲3.8k2.50
[PDF]Learning to Switch with Stability and Convergence Guarantees: Policy Gradient for State-Independent Controller Switching in Linear Systems▼1361.33
[PDF]Auditing a Learned Admission Gate for Offline-to-Online Safe RL: Distinct Certificates and Public Comparator Failures▼1361.33
[PDF]SAFTER: Safety-Aware Filtered Training for Efficient and Robust Reinforcement Learning with Closed-Form Backup CBFs▼11k2.33
[PDF]Do We Need Cost Critics? Local Cost Relabeling for Offline Safe Reinforcement Learning▼5.8k2.33
[PDF]Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual Regularization▲9.2k2.67
[PDF]C-Steering: Constrained Noise-Space Steering of Behaviour-Cloned Flow Policies for Offline Safe RL▼1361.33
[PDF]Discovering Safety Spectra in Autonomous Driving via Constrained Adversarial Self-Play▼4.5k2.67
[PDF]Generative Bellman Flow: Mitigating the CVaR Gradient Bottleneck in Risk-Sensitive Reinforcement Learning▼4.3k2.00
[PDF]RISE: Enhancing Safety for End-to-End Autonomous Driving through Risk-Aware Energy-Guided Diffusion Planner▼4.3k2.00
[PDF]Dynamic Elite Replay: Learning Beyond Suboptimal Experts in Human-in-the-Loop Reinforcement Learning▼4.3k2.00
[PDF]When Is One Reading Enough? Decision-Relevant Ambiguity in Constrained Reinforcement Learning▲6.1k2.00
[PDF]CASTLE: CAUSALLY ATTRIBUTED SOFT CONJUNC TIONS FOR SOUND AND INFORMATIVE SAFETY CERTIFI CATES▼1361.33
[PDF]When Zero Cost Does Not Mean Safe: Response Delay and Policy Delivery in Resource-Constrained Reinforcement Learning▼1.3k1.75
[PDF]Beyond Safe Demonstrations: Failure-Informed Flow Policies for Offline Safe Reinforcement Learning▲5103.00
[PDF]Model-Based Proactive Cost Generation for Learning Safe Policies Offline with Limited Violation Data▲3.0k2.33
[PDF]Semiparametrically Efficient Off-Policy Evaluation and Learning in Constrained Markov Decision Processes▼4.3k2.00
[PDF]RBGA: Residual-Budget Guide Arbitration for Offline-to-Online Safe Reinforcement Learning in Dexterous Manipulation▼4.3k2.00
[PDF]Different Bonuses, Similar Outcomes: Understanding Auxiliary Reward Non-Separation in PPO▼1361.33
[PDF]AerialGenesis: Language-Conditioned Predictive Safety Fields for Generative UAV Navigation▲3.0k2.33
[PDF]Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning▲5103.00
Withdrawn or desk rejected (6)
[PDF]It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption BankWithdrawn1.33