{"acceptedBy":null,"aliases":[],"change":{"last4":7,"percent":null,"prior4":0},"dateBasis":"publication","description":{"editedBy":{"actor":"ai","name":"Codex","on":"2026-11-07"},"state":"ai_edited"},"href":null,"itemCount":7,"key":"reinforcement-learning","kind":"editor_concept","name":"Reinforcement learning","neighbours":[{"key":"cybernetic-feedback-loops","kind":"editor_concept","name":"Cybernetic feedback loops","provenance":"human","relation":"related_to","weight":0}],"recordCount":7,"relatedItems":[],"relatedRecords":[{"provenance":"routed from the papers-huggingface monitor","publishedAt":"2026-11-04T13:24:54Z","reason":"reinforcement-learning","source":"papers-huggingface","summary":"What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? (routed from the papers-huggingface monitor, 2026-11-04).","title":"What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?","url":"https://arxiv.org/abs/2611.06483"},{"provenance":"routed from the web-shipped monitor","publishedAt":"2026-10-31T00:00:00Z","reason":"reinforcement-learning","source":"web-shipped","summary":"Multi-objective optimisation for drone allocation and routing in humanitarian aid delivery: a reinforcement learning-based approach (routed from the web-shipped monitor, 2026-10-31).","title":"Multi-objective optimisation for drone allocation and routing in humanitarian aid delivery: a reinforcement learning-based approach","url":"https://www.tandfonline.com/doi/full/10.1080/00207543.2026.2752509"},{"provenance":"routed from the web-machines-on-machines monitor","publishedAt":"2026-10-31T00:00:00Z","reason":"reinforcement-learning","source":"web-machines-on-machines","summary":"Deep reinforcement learning-driven assessment and personalized educational strategies for college students using innovation and entrepreneurship-related educational proxies (routed from the web-machines-on-machines monitor, 2026-10-31).","title":"Deep reinforcement learning-driven assessment and personalized educational strategies for college students using innovation and entrepreneurship-related educational proxies","url":"https://link.springer.com/article/10.1007/s44163-026-02567-4"},{"provenance":"routed from the web-anth-us monitor","publishedAt":"2026-10-31T00:00:00Z","reason":"reinforcement-learning","source":"web-anth-us","summary":"GitHub - madhavmadupu/sonar: S.O.N.A.R. - Simulated Optimization & Neural Actuation Runtime: Sim-to-Real reinforcement learning pipeline with MuJoCo/MJX domain randomization, ONNX/TensorRT sub-millisecond compilation, and Control Barrier Function safety filters. (routed from the web-anth-us monitor,","title":"GitHub - madhavmadupu/sonar: S.O.N.A.R. - Simulated Optimization & Neural Actuation Runtime: Sim-to-Real reinforcement learning pipeline with MuJoCo/MJX domain randomization, ONNX/TensorRT sub-millisecond compilation, and Control Barrier Function safety filters.","url":"https://github.com/madhavmadupu/sonar"},{"provenance":"routed from the papers-huggingface monitor","publishedAt":"2026-10-29T00:00:00Z","reason":"reinforcement-learning","source":"papers-huggingface","summary":"On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning (routed from the papers-huggingface monitor, 2026-10-29).","title":"On the Origin and Evolution of Training-Inference Mismatch in LLM Reinforcement Learning","url":"https://arxiv.org/abs/2610.40945"},{"provenance":"routed from the papers-huggingface monitor","publishedAt":"2026-10-29T00:00:00Z","reason":"reinforcement-learning","source":"papers-huggingface","summary":"Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps (routed from the papers-huggingface monitor, 2026-10-29).","title":"Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps","url":"https://arxiv.org/abs/2610.39264"},{"provenance":"routed from the papers-huggingface monitor","publishedAt":"2026-10-26T00:00:00Z","reason":"reinforcement-learning","source":"papers-huggingface","summary":"When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing (routed from the papers-huggingface monitor, 2026-10-26).","title":"When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing","url":"https://arxiv.org/abs/2610.35497"}],"schemaVersion":1,"series26":[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,6,1],"series8":[0,0,0,0,0,0,6,1],"weeksOfHistory":2}