conftrace_

policy optimization

771 papers

Explore in graph

Also known as

POLO PO

Co-occurring keywords · papers mentioning both

reinforcement learning (237) markov decision process (81) offline reinforcement learning (69) large language model (56) model-based reinforcement learning (53) sample efficiency (44) deep reinforcement learning (43) safe reinforcement learning (40) continuous control (39) value function (37)

Papers

Adaptive KL Control for Direct Preference Optimization in Instruction-Following LLMs AAAI 2026 APPO: Attention-guided Perception Policy Optimization for Video Reasoning CVPR 2026 AT²PO: Agentic Turn-based Policy Optimization via Tree Search ACL 2026 Behavior Regularization with Flow Latent Policy for Offline Reinforcement Learning AAAI 2026 Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning AAAI 2026 Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs CVPR 2026 Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning AAAI 2026 Boundary-Guided Policy Optimization for Memory-efficient RL of Diffusion Large Language Models ACL 2026 Calibration-Aware Policy Optimization for Reasoning LLMs ACL 2026 Causal Discovery for Efficient Offline RL with Factored Action Spaces CLeaR 2026 CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization CVPR 2026 Conformal Constrained Policy Optimization for Cost-Effective LLM Agents AAAI 2026 Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning AAAI 2026 COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs CVPR 2026 D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss AAAI 2026 d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models ACL 2026 Dynamic Important Example Mining for Reinforcement Finetuning CVPR 2026 Efficient Preference Alignment via Pareto Exploration (Student Abstract) AAAI 2026 End-Effector Cartesian Velocity Control for Redundant Loader Cranes Using Reinforcement Learning (Abstract Reprint) AAAI 2026 End-to-End Optimization of LLM-Driven Multi-Agent Search Systems via Heterogeneous-Group-Based Reinforcement Learning ACL 2026 Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning ACL 2026 Experience-driven Multi-turn Reinforcement Learning for GUI Agents ACL 2026 Foresight Optimization for Strategic Reasoning in Large Language Models ACL 2026 From log 𝜋 to 𝜋: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight ACL 2026 GEM: Generative Entropy-Guided Preference Modeling for Few-Shot Alignment of LLMs AAAI 2026