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
75 results for “keyword:"off policy"” in ICLR 2027. 9 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO▼4.3k2.00
[PDF]Evolution Only When Needed: Triggered Evolutionary Data Injection for Off-Policy Reinforcement Learning▲3.0k2.33
[PDF]Delayed Heuristic-Behavior-Target Coupling for Off-Policy Reinforcement Learning in Inventory Control▼5.3k1.33
[PDF]Semiparametrically Efficient Off-Policy Evaluation and Learning in Constrained Markov Decision Processes▼4.3k2.00
[PDF]ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning▲5.4k3.00
[PDF]When More Candidates Hurt: A Proposal–Evidence Reliability Frontier for Causal Selection▼1.3k1.80
[PDF]SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning▲3.0k2.33
[PDF]EPIC: Rethinking Trust Regions for Autoregressive LLM Policies via Exact-KL Prefix Importance-ratio Clipping▼1.2k1.67
[PDF]REVEALING AFTER OVERWRITING: AN EXPONENTIAL POMDP OPE LOWER BOUND UNDER HISTORY-DEPENDENT LOGGING▲143.33
Withdrawn or desk rejected (9)
[PDF]When Agents Change Their Own Test: Prospective Target Preservation under Candidate-Induced Task ExpansionWithdrawn1.33
[PDF]AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web AgentsWithdrawn