Deep RL

RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning RSS 2025 RLLTE: Long-Term Evolution Project of Reinforcement Learning AAAI 2025 RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression CVPR 2025 RLTHF: Targeted Human Feedback for LLM Alignment ICML 2025 RL + Transformer = A General-Purpose Problem Solver ACL 2025 Robots Learning Through Physical Interactive Intelligence AAAI 2025 Robust Finite-Memory Policy Gradients for Hidden-Model POMDPs IJCAI 2025 Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning ICLR 2025 RobustLight: Improving Robustness via Diffusion Reinforcement Learning for Traffic Signal Control ICML 2025 Robustness to Spurious Correlations via Dynamic Knowledge Transfer IJCAI 2025 Robust Noise Attenuation via Adaptive Pooling of Transformer Outputs ICML 2025 RobustZero: Enhancing MuZero Reinforcement Learning Robustness to State Perturbations ICML 2025 S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning ACL 2025 Safety Representations for Safer Policy Learning ICLR 2025 Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports RSS 2025 SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization ACL 2025 Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation AAAI 2025 Scaling Test-Time Compute Without Verification or RL is Suboptimal ICML 2025 SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning ICCV 2025 Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability JMLR 2025 Select before Act: Spatially Decoupled Action Repetition for Continuous Control ICLR 2025 Self-Consistent Model-based Adaptation for Visual Reinforcement Learning IJCAI 2025 Self-Correcting Code Generation Using Small Language Models EMNLP 2025 Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation ACL 2025 SeqMvRL: A Sequential Fusion Framework for Multi-view Representation Learning CVPR 2025