{"total":4,"items":[{"citing_arxiv_id":"2607.08340","ref_index":3,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Spectral Analysis of Dueling Q-Learning","primary_cat":"cs.LG","submitted_at":"2026-07-09T10:29:22+00:00","verdict":"CONDITIONAL","verdict_confidence":"HIGH","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Unregularized centered dueling Q-learning converges under a joint spectral radius condition, with value and advantage acting as distinct gains on common and differential Q components.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22145","ref_index":57,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Zero-shot sim-to-real transfer of independently trained RL policies for cart-pole swing-up and stabilization is achieved via sensitivity-guided domain randomization, linear curriculum learning, and first-order action smoothing with Simulink switching logic.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09825","ref_index":26,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"An Agency-Transferring Model-Free Policy Enhancement Technique","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A model-free RL method arbitrates between a functional baseline policy and a learning policy, transferring agency over time to yield a standalone policy with high goal-reaching rates and competitive returns on continuous-control tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.09439","ref_index":40,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Tracking the Effective Surface Area of Non-Convex Satellites","primary_cat":"eess.SY","submitted_at":"2026-06-08T12:48:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Backstepping control tracks effective surface area of non-convex satellites for drag-based orbital control, with asymptotic stability proofs and an extension for solar panel exposure.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}