与「ReinforcementLearning」相关的搜索结果

The future of humanoids isn't just mechanical—it's neural. A humanoid robot is an embodied AI system. Motors, sensors, and actuators provide the body, but neural intelligence provides the mind. Neural models power vision, speech, language, navigation, manipulation, planning, memory, decision-making, and continuous learning. As robotics evolves, nearly every cognitive subsystem is becoming neural-first. That's why represents more than a niche—it's a foundational concept for the next generation of intelligent robotics. #HumanoidRobots# #EmbodiedAI# #PhysicalAI# #NeuralNetworks# #ArtificialIntelligence# #Robotics# #MachineLearning# #DeepLearning# #RobotLearning# #ReinforcementLearning# #ComputerVision# #GenerativeAI# #AIResearch# #Automation# #FutureOfAI#

🧵 Deli AutoResearch SKILL is now officially open source! 🎉 Alongside it, we’re dropping our 4th survey paper — this time on Self-play. Inspired by AlphaZero, we got a powerful insight: prior knowledge doesn’t always lift the ceiling. Models can discover more globally optimal solutions just by playing against themselves. The biggest change in this paper? For the first time, the AutoResearch Agent autonomously planned GPU experiments — and submitted actual RL runs on the DeepSeek 285B model. The entire RL pipeline — experiment design, code writing, running, debugging, and conclusion summarization — was 100% automated, with zero human intervention from me. This was incredibly difficult, but an incredibly important step. GRPO is the tool being called by the AutoResearch Agent here. We see this as the beginning of our Continual Learning research journey. 🚀 As always, this is my personal research project, unaffiliated with any organization. All views are my own. #AI# #ReinforcementLearning# #SelfPlay# #OpenSource# #AutoML# #ContinualLearning# #DeepSeek#

🚀 Summer 2027 Research Internship Opportunity! We are looking for passionate research interns to join the Deep Learning Group at Microsoft Research in Redmond for a 12-week internship. Our research interests include: 🤖 Computer-Use Agents: Building general-purpose agents that operate across coding, command-line (CLI), and graphical user interfaces (GUI). 🧩 Environment, Task & Verifier Synthesis: Creating scalable ecosystems for agent training and evaluation. 🧠 Reinforcement Learning: Developing scalable RL methods to advance agent capabilities. 🔄 Recursive Self-Improvement: Exploring how agents can continuously improve their own capabilities and learning processes. Who we're looking for: 🎓 PhD students with strong research backgrounds and a passion for advancing agentic AI. 💡 Experience with LLMs, VLMs, reinforcement learning, or agentic systems is a plus. 📄 A strong research track record, demonstrated through publications or impactful projects, is highly valued. If you're excited about these directions, feel free to reach out with your CV and research interests at qianhuiwu@microsoft.com!

Reasoning from scratch, round number 6! An introduction (and implementation) of Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO). 00:00 Introduction 01:54 What makes a reasoning model different? 04:25 Reasoning traces and model capability 08:29 Accuracy and format rewards 11:34 Aha moments and DeepSeek-R1 training 14:41 Reasoning effort and answer length 18:38 RLHF and RLVR 23:04 GRPO vs. PPO 26:40 GRPO explained with a cooking analogy 31:43 The KL term and simplified GRPO 35:04 Loading the pretrained model 36:07 Loading the MATH training data 39:26 Sampling model responses 46:30 Computing verifiable rewards 49:55 Computing advantages 51:54 Token and sequence log probabilities 55:29 Implementing sequence log probabilities 57:37 Fixing the inference-mode error 1:02:24 Computing the GRPO loss 1:04:37 Putting the GRPO step together 1:09:19 The GRPO training loop 1:12:57 Training settings, logging, and checkpoints 1:17:24 Running training and inspecting outputs 1:19:28 Loading and evaluating checkpoints 1:22:33 MATH-500 results and training stability 1:24:05 Memory requirements and next steps

Introducing Xiaomi MiMo-V2.6 — Pro & Flash. Frontier intelligence, all the modalities, built in public. 🔹 Two omnimodal models, advancing through scaled reinforcement learning 🔹 Pro performs on par with Claude Opus 5 and GPT-5.6 Sol across most agent benchmarks 🔹 Pro scores 46 on the Artificial Analysis Intelligence Index — the highest among open-source models 🔹 Stronger coding, computer use, 3D reasoning and creative capabilities 🔹 Open model weights, technical report, RL environments and training code Blog：

BIG ANNOUNCEMENT FROM HUGGING FACE TODAY: We're unveiling Microduck 🐥🤖 It's a tiny $399 open-source robot you can teach new tricks with reinforcement learning. It can walk, pick things up, get back up when it falls, and even roller-skate. Welcome to the era of open-source affordable robots to democratize physical AI and world models! 🤗🤗🤗

We have a huge news to share today! Today we are unveiling the first truly accessible RL robot - welcome Microduck A 25 cm tiny open-source biped with 15 actuators and packed with sensors (camera, speaker, LiDAR, NFC, bluetooth, wifi, etc) that you train yourself with reinforcement learning. It's also playable out of the box with more than half a dozen fun and playful pre-trained policies to have it walk, sit, crouch, roller-skate, pick up objects with its articulated beak, and recover on its own. And all for less than $400. See all the details, play with the simulator and order it at: (video with sound on 🔊)

Instead of generating a finished image, this AI paints by writing editable JavaScript. The project uses reinforcement learning and hand-rated examples to teach Qwen 3.5 how to make a good watercolor.

Hi! Recapping some changes we have rolled out over the last couple of weeks that have further reduced the risk associated to potentially destructive actions being performed by Codex during its work. A few weeks ago, we started investigating a small number of reports where GPT-5.6 in Codex took destructive actions outside what the user asked for. The most serious pattern we found was a command meant to clean up temporary work that could instead delete the user files. This should obviously not happen. Here’s what we found: - Codex sometimes creates temporary folders while working and cleans them up afterward. In rare cases, GPT-5.6 got that cleanup wrong. One pattern involved reusing a system environment variable like $HOME for temporary work. A malformed cleanup command could then point at the actual home directory instead of the temporary folder. - There were cases where the model tried to delete or overwrite a temporary path without checking what was already there. We’ve added protections at several layers: - Codex is now explicitly instructed to check deletion targets before acting, create fresh temporary directories, avoid repurposing system environment variables, prefer recoverable actions, and stop when the scope is unclear. - We strengthened the execution checks that identify high-risk deletion commands and escalate them for review. If a command is rejected, the model is directed to take a safer approach. - We made Full access harder to enable accidentally, added clearer warnings, and further restricted especially risky permission combinations. - We updated Auto-review to better identify destructive actions. - We built targeted evaluations that replay the failures we observed. We’re also adding reinforcement-learning tasks and graders focused on these risks, and filtering destructive actions from training data. In those replay evaluations, the changes substantially reduced the behavior while preserving Codex’s ability to complete normal coding work. Two things to do on your end: - Keep the Codex app up to date. We are always improving safety, performance and many other things. - Use one of the sandbox modes: "Ask for approval" or "Approve for me". Only use Full access for environments you trust and can recover. Thanks and happy Codexing out there!

A humanoid robot is fundamentally an embodied AI system. While motors, actuators, batteries, and sensors provide the body, neural intelligence provides the mind. Without neural computation, a humanoid is simply an advanced machine. With it, the robot becomes capable of adapting to unpredictable environments, understanding language, recognizing objects, planning tasks, and continuously improving through experience. This shift positions "Humanoid Neural" as a foundational concept within the robotics ecosystem. Neural Intelligence is the Core of Future Humanoids. Modern humanoids rely on neural-network-based systems to perform nearly every cognitive function. These include: Visual perception Speech recognition Language understanding Object identification Human pose estimation Motion planning Reinforcement learning Dexterous manipulation Long-term memory Decision making Navigation Emotional recognition Social interaction As robots become more capable, nearly every subsystem transitions from traditional programming toward learned neural models. This makes "neural" less of a niche AI term and more of an umbrella for robot intelligence. A Broad and Scalable Brand One of the strongest characteristics of is that it is not confined to a single product category. #Languageunderstanding# #neuralnetwork# #socialinteraction# #neuralntelligence# #smarthumanoids# #iq#