conftrace_

monte carlo rollout

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

socratic tutoring (1) teacher-student simulation (1) hierarchical task-oriented language (1) operational model (1) closed-loop decision-making (1) pedagogical effectiveness (1) descriptive model (1) gap-dependent regret (1) adaptive multi-step bootstrap (1) multi-horizon preference optimization (1)

Papers

Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring ACL 2026 Adaptive Prior-Dependent Correction Enhanced Reinforcement Learning for Natural Language Generation AAAI 2021 Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap COLT 2021 On the role of planning in model-based deep reinforcement learning ICLR 2021 Acting and Planning Using Operational Models AAAI 2019