Deep RL

PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement Learning CVPR 2026 Perceiving the Knowledge Boundary: Uncertainty-Guided Exploration and Imagination for World Models AAAI 2026 Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization AAAI 2026 Policy Zooming: Adaptive Discretization-based Infinite-Horizon Average-Reward Reinforcement Learning AAAI 2026 Potent but Stealthy: Rethink Profile Pollution Against Sequential Recommendation via Bi-Level Constrained Reinforcement Paradigm AAAI 2026 PQDA:Policy-Aligned Q-Consistency Meets Decoupled Augmentation for Generalizable Visual RL AAAI 2026 Promoting Efficient Reasoning with Verifiable Stepwise Reward AAAI 2026 PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and VLM-Guided Optimization CVPR 2026 Provably Safe Offline-to-Online RL: Decoupling Learning from Data-Driven Safety Enforcement ACL 2026 PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis AAAI 2026 Push-and-Step: From RL-Based Balance Recovery to Physical Simulation of Dense Crowds CVPR 2026 ReACT: Reward-informed Autoregressive Decision CAD Transformer AAAI 2026 ReasonAct: Progressive Training for Fine-Grained Video Reasoning in Small Models AAAI 2026 Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards ACL 2026 RehearseVLA: Simulated Post-Training for VLAs with Physically-Consistent World Model CVPR 2026 Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models WACV 2026 Reinforcement Learning Without Explicit Rewards: Theory and Practice AAAI 2026 Reliability-Guaranteed and Reward-Seeking Sequence Modeling for Model-Based Offline Reinforcement Learning AAAI 2026 Reliable Policy Transfer for Safety-Aware End-to-End Driving with Deep Reinforcement Learning CVPR 2026 Revisiting TD Target Aggregation under Uncertainty in Q-Learning UAI 2026 Reward Redistribution via Gaussian Process Likelihood Estimation AAAI 2026 Risk-Sensitive Exponential Actor Critic AAAI 2026 RL-ScanIQA: Reinforcement-Learned Scanpaths for Blind 360deg Image Quality Assessment CVPR 2026 RLSLM: A Hybrid Framework Combining Reinforcement Learning and a Rule-based Social Locomotion Model for Socially-aware Navigation AAAI 2026 Robust Adaptive Multi-Step Predictive Shielding (Student Abstract) AAAI 2026