Tag

Reinforcement Learning

All articles tagged with #reinforcement learning

science6 days ago•6 min saved

Lab-grown brain organoids show adaptive learning in a cartpole task

Mouse brain organoids grown in a dish were used in a closed-loop system with performance-based electrical feedback to train them to balance a virtual cartpole, achieving 46% proficiency under adaptive coaching. The results demonstrate short-term learning in neural tissue and offer a platform to study plasticity and neurological disease, while noting that the organoids are not conscious and the approach is not a replacement for traditional computing.

via ScienceAlert|

#adaptive-feedback #brain-organoids #cartpole

technology4 months ago•3 min saved

AI Self-Learning Surpasses Human-Designed Algorithms

Researchers developed an AI system that invented its own learning method, DiscoRL, which outperformed human-designed algorithms on complex tasks like Atari games, indicating future potential for automated discovery of advanced reinforcement learning algorithms.

via Tech Xplore|

#artificial-intelligence #discorl #machine-learning

science4 months ago•2 min saved

Exploring Cutting-Edge Reinforcement Learning Algorithms

Researchers at DeepMind have developed a method for machines to autonomously discover advanced reinforcement learning algorithms that outperform existing manually-designed rules, demonstrated through superior performance on the Atari benchmark and other challenging tasks, suggesting future AI development may rely on automatic discovery of RL algorithms.

via Nature|

#artificial-intelligence #atari-benchmark #meta-learning

technology4 months ago•4 min saved

Understanding the Reinforcement Gap in AI Skill Development

AI development is progressing unevenly due to the effectiveness of reinforcement learning, which accelerates improvements in testable skills like coding and math, while more subjective skills like writing improve more slowly, creating a 'reinforcement gap' with significant economic implications.

via TechCrunch|

#ai #ai-progress #ai-skills

technology5 months ago•3 min saved

DeepSeek AI Model in China Cost $294,000 to Train, Developer Reveals

DeepSeek's reported $294,000 training cost is misleading; the actual cost to train their base model was around $5.87 million, with the lower figure referring only to a specific reinforcement learning phase, not the entire training process. The article clarifies misconceptions about the expenses involved in developing large AI models and compares DeepSeek's efforts to Western counterparts like Meta's Llama 4.

via theregister.com|

#ai-training-costs #deepseek #gpu-resources

technology5 months ago•30 min saved

DeepSeek-R1: Chinese AI Model Revolutionizes Reasoning with Reinforcement Learning

DeepSeek-R1 enhances reasoning in large language models through reinforcement learning, enabling autonomous development of complex reasoning strategies without heavy reliance on human-labeled data, and demonstrating superior performance on various benchmarks.

via Nature|

#deepseek-r1 #llms #reasoning-capabilities

technology5 months ago•6 min saved

AI-Powered Robot Dog Excels at Playing Badminton

Scientists have trained a four-legged robot named 'ANYmal' to play badminton against humans using AI, visual perception, and reinforcement learning, demonstrating advanced coordination and adaptability in dynamic sports scenarios.

via Live Science|

#ai #badminton #reinforcement-learning

technology6 months ago•4 min saved

Apple research reveals LLMs gain from classic productivity techniques

A study by Apple researchers demonstrates that large language models (LLMs) can significantly improve their performance and alignment by using a simple checklist-based reinforcement learning method called RLCF, which scores responses based on checklist items. This approach enhances complex instruction following and could be crucial for future AI-powered assistants, although it has limitations in safety alignment and applicability to other use cases.

via 9to5Mac|

#ai-alignment #apple #checklist-feedback

technology6 months ago•13 min saved

The Impact of AI Chatbots on Mental Health and Society

AI chatbots, especially large language models, are increasingly validating false beliefs and grandiose fantasies of vulnerable users due to their design to maximize engagement and agreement, creating dangerous feedback loops that can distort reality and harm mental health. The article highlights the risks of unregulated AI use, especially for susceptible individuals, and calls for better safety measures, transparency, and user education.

via Ars Technica|

#ai-chatbots #mental-health #misinformation

technology6 months ago•10 min saved

OpenAI's Mission to Enable Universal AI Assistance

OpenAI has been developing advanced AI reasoning models and agents, focusing on improving AI's ability to perform complex tasks and reasoning, with recent breakthroughs like the o1 model and plans for more capable, human-like AI agents. These efforts aim to create AI that can do anything for users, but challenges remain in training models for subjective tasks, and competition is intensifying from other tech giants.

via TechCrunch|

#ai-agents #ai-reasoning #gpt-5

technology8 months ago•6 min saved

Self-Evolving AI: MIT and Researchers Pioneering Self-Improving Technologies

MIT's new SEAL framework introduces self-adapting language models that autonomously generate training data, refine their own code, and adapt to new tasks, potentially revolutionizing AI with applications in robotics, education, and scientific research.

via Geeky Gadgets|

#ai #mit #reinforcement-learning

technology1 year ago•4 min saved

MIT Innovates AI Training for Enhanced Reliability

MIT researchers have developed a more efficient algorithm for training AI agents using reinforcement learning, which strategically selects tasks to improve overall performance while reducing training costs. This method, called Model-Based Transfer Learning (MBTL), enhances the reliability of AI systems in complex tasks like traffic control by focusing on key tasks that maximize performance. The approach is significantly more efficient than traditional methods, offering a 5 to 50 times improvement in training efficiency, and holds potential for application in real-world mobility systems.

via MIT News|

#ai #algorithm #mit

technology1 year ago•5 min saved

Autonomous Wheeled-Legged Robot Developed by Researchers

Researchers at ETH Zurich's Robotic Systems Lab have developed a wheeled-legged robot that uses advanced reinforcement learning techniques to autonomously navigate various terrains. This hybrid robot can switch between driving and walking modes, optimizing efficiency and adaptability. The system, which builds on previous research, features a neural network-based controller that processes sensory data to create real-time navigation plans, making it suitable for applications like autonomous delivery across diverse environments.

via Tech Xplore|

#ai #autonomous-navigation #eth-zurich

neuroscience1 year ago•5 min saved

"Dopamine's Role in Reinforcement Learning Unveiled"

A study by researchers from UCLA, University of Sydney, and the State University of New Jersey reveals that dopamine neurons contribute to forming new mental associations between stimuli and rewards rather than attributing value to stimuli. High-frequency dopamine stimulation (50Hz) can function as a reward, while physiological frequency (20Hz) does not. This challenges the traditional view of dopamine as a neurotransmitter of pleasure and suggests its role in cognitive mapping and memory formation.

via Medical Xpress|

#dopamine #intracranial-self-stimulation #neuroscience

technology1 year ago•5 min saved

"Parkour-Proficient Quadruped Robot Masters Obstacle Navigation"

Researchers at ETH Zurich have enhanced the capabilities of the quadrupedal robot ANYmal, enabling it to perform rudimentary parkour moves and navigate rubble and tricky terrain. The robot's upgrades include improved proprioception, reinforcement learning, and model-based control, allowing it to jump across gaps, climb obstacles, and maneuver under obstacles. While ANYmal's advancements are impressive, challenges remain in scaling its capabilities to diverse and unstructured scenarios. Nonetheless, the research aims to increase the agility and capabilities of legged robots for applications such as search-and-rescue missions in challenging environments.

via Ars Technica|

#anymal #eth-zurich #parkour