explore | Grilled Cheese

Stockholm University is offering a PhD position in machine learning, with a focus on reinforcement learning, bandit methods, and multi-agent systems.

mlscientist.com/phd-machine-...

#reinforcementlearning

Congrats Ivelina for your PhD defense 🎓 on Temporal #RuleInduction with #ReinforcementLearning for explainable representation of activities. She addresses activities beyond sequential actions, but with concurrency relations, learned from reward
#TemporalRules #XAI
📽️ www.youtube.com/watch?v=iz7x...

Co-Design Gym is a new benchmark suite for jointly optimizing an agent's embodiment and control policy, addressing the limitation that most existing benchmarks fix the agent's design. It targets robotics and other…

#Robotics #AI #ReinforcementLearning #Benchmark
https://arxiv.org/abs/2610.02366

EVOL uses a knowledge tracing simulator to synthesize expert learning paths via evolutionary search and distill them into a deployment-free policy for learning path recommendation. The method borrows from…

#Robotics #AI #EdTech #ReinforcementLearning
https://arxiv.org/abs/2610.03273

La semana en [Blue Chip]. Jueves 1: "Cómo hacemos que un modelo razone (V): aprendizaje por refuerzo con feedback humano (RLHF)" ignaciogavilan.com/como-hacemos... #RLHF #ReinforcementLearning #ReasoningModels #ModelosRazonadores #LRM #LargeReasoningModels #LLM #LargeLanguageModels #IA #AI

La semana en [Blue Chip]. Lunes 28-Sep: "Cómo hacemos que un modelo razone (IV): aprendizaje por refuerzo basado en recompensas verificables (RLVR)" ignaciogavilan.com/como-hacemos... #RLVR #GRPO #ReinforcementLearning #AprendizajePorRefuerzo #ModelosRazonadores #ReasoningModels #IA #AI #LLM

Fine-tuning a small search agent with multi-turn RL on Amazon SageMaker AI can give it frontier-model reliability for your tools at lower…

#SageMaker #LLM #ReinforcementLearning
https://aws.amazon.com/blogs/machine-learning/fine-tune-a-search-agent-with-multi-turn-rl-on-amazon-sagemaker-ai/

AI researchers highlight how alignment between numerical computations and model-parallel execution (MoE routing) is crucial for achieving reliable reinforcement learning outcomes.

#ai #technology #artificialintelligence #reinforcementlearning #moe #news

Not every problem deserves the same amount of thinking. When2Think brings instance-adaptive reasoning to AI—rewarding correct answers, #AI #MachineLearning #LLM #ReinforcementLearning

https://freegardner.com/synapse/when2think-ai-adaptive-reasoning-efficiency.html

Hoy en [Blue Chip]: "Cómo hacemos que un modelo razone (V): aprendizaje por refuerzo con feedback humano (RLHF)" ignaciogavilan.com/como-hacemos... #RLHF #ReinforcementLearning #ReasoningModels #ModelosRazonadores #LRM #LargeReasoningModels #LLM #LargeLanguageModels #IA #AI

Researchers propose a Real-to-Sim-to-Real framework with an information-theoretic cost function to reduce the sim-to-real gap, integrating with RL algorithms like PPO and SAC and optionally using differentiable simulators.

#Robotics #SimToReal #ReinforcementLearning
https://arxiv.org/abs/2503.10118

New arXiv work reviews progress on efficient, robust, instance-adaptive sequential decision-making in RL and bandits, with applications to robotics and LLMs.

#Robotics #AI #MachineLearning #ReinforcementLearning
https://arxiv.org/abs/2504.09192

RLTL;DR: 自己生成フィードバックの内部化によるLLMの自己改善

Appleが発表したRLTL;DRは、自己生成フィードバックの内部化によって高難度タスクの自己改善を実現する新しいパラダイムである。

#LLM #ReinforcementLearning #Self-Improvement #MethodsandAlgorithms

[Blue Chip]: "Cómo hacemos que un modelo razone (V): aprendizaje por refuerzo con feedback humano (RLHF)" ignaciogavilan.com/como-hacemos... #RLHF #ReinforcementLearning #ReasoningModels #ModelosRazonadores #LRM #LargeReasoningModels #LLM #LargeLanguageModels #IA #AI

New arXiv work shows vision-language-action models can be reinforcement-learning fine-tuned across diverse simulated scenes using generative 3D worlds, avoiding costly sim-to-real fixes and scene-specific…

#robotics #AI #simtoreal #reinforcementlearning
https://arxiv.org/abs/2603.18532

New paper proposes Reward-rate Policy Gradient (RPG) for ML engineering agents, adapting continuous-time RL and SMDPs to optimize reward per unit time rather than cumulative reward alone. This addresses…

#AI #ReinforcementLearning #MachineLearning #MLOps
https://arxiv.org/abs/2609.36393