Reinforcement Learning

Safety Representations for Safer Policy Learning ICLR 2025 Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports RSS 2025 SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies CoRL 2025 Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation UAI 2025 Sample and Oracle Efficient Reinforcement Learning for MDPs with Linearly-Realizable Value Functions COLT 2025 Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction ICML 2025 Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens JMLR 2025 Sample-Efficient Online Control Policy Learning with Real-Time Recursive Model Updates CoRL 2025 Sample-Optimal Agnostic Boosting with Unlabeled Data ICML 2025 Sampling-based System Identification with Active Exploration for Legged Sim2Real Learning CoRL 2025 SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization ACL 2025 SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learning RSS 2025 Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search ICML 2025 Scalable spectral representations for multiagent reinforcement learning in network MDPs AISTATS 2025 Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation AAAI 2025 Scaling Laws for Pre-training Agents and World Models ICML 2025 Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining ICLR 2025 Scaling Test-Time Compute Without Verification or RL is Suboptimal ICML 2025 Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning ICML 2025 SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning ICCV 2025 Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments CVPR 2025 SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Arguments EMNLP 2025 Score as Action: Fine Tuning Diffusion Generative Models by Continuous-time Reinforcement Learning ICML 2025 Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability JMLR 2025 Score-Based Diffusion Policy Compatible with Reinforcement Learning via Optimal Transport ICML 2025