{"total":16,"rows":[{"id":"2411.16905","title":"Boundless Socratic Learning with Language Games","created":"2024-11-25","cited_by_count":12,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2412.04233","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","created":"2024-12-05","cited_by_count":11,"area":null},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2311.08290","title":"On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling","created":"2023-11-14","cited_by_count":6,"area":null},{"id":"2407.16312","title":"MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2609.06107","title":"DataFlex-RL: An Evaluation Platform for RLVR Data Policies","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2506.07134","title":"Monotone and Conservative Policy Iteration Beyond the Tabular Case","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2603.28416","title":"Evolutionary Discovery of Reinforcement Learning Algorithms via Large Language Models","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.02469","title":"Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2608.06481","title":"Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2504.14636","title":"When Search Teaches Style: Causal Internalization of Tactical Priors in AlphaZero","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2512.24145","title":"When Does Pairing Seeds Reduce Variance? Evidence from a Multi-Agent Economic Simulation","created":"2025-12-30","cited_by_count":0,"area":null},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2609.05508","title":"When Do Options Help? Policy Necrosis and Redundant Coverage in Option-Critic","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2610.15328","title":"Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}