<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Reinforcement Learning on KAD</title>
    <link>https://www.kad8.com/tags/reinforcement-learning/</link>
    <description>Recent content in Reinforcement Learning on KAD</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>© 2026 </copyright>
    <lastBuildDate>Sat, 26 Sep 2026 00:31:33 +0800</lastBuildDate><atom:link href="https://www.kad8.com/tags/reinforcement-learning/index.xml" rel="self" type="application/rss+xml" />
    
    <item>
      <title>ULTRA Lets Humanoid Robots Perform Whole-Body Tasks From Sparse Goals</title>
      <link>https://www.kad8.com/ai/ultra-lets-humanoid-robots-perform-whole-body-tasks-from-sparse-goals/</link>
      <pubDate>Sat, 26 Sep 2026 00:31:33 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/ultra-lets-humanoid-robots-perform-whole-body-tasks-from-sparse-goals/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/ultra-lets-humanoid-robots-perform-whole-body-tasks-from-sparse-goals/featured-Robot_demonstrating_advanced.jpg" />
    </item>
    
    <item>
      <title>Machineslop: Why AI-Generated Code Is Becoming Unreadable</title>
      <link>https://www.kad8.com/ai/machineslop-why-ai-generated-code-is-becoming-unreadable/</link>
      <pubDate>Sun, 13 Sep 2026 18:37:50 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/machineslop-why-ai-generated-code-is-becoming-unreadable/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/machineslop-why-ai-generated-code-is-becoming-unreadable/featured-Robot_hand_assembling_binary_code.jpeg" />
    </item>
    
    <item>
      <title>Why OpenAI and Anthropic Are Buying Thousands of Macs for AI</title>
      <link>https://www.kad8.com/ai/why-openai-and-anthropic-are-buying-thousands-of-macs-for-ai/</link>
      <pubDate>Mon, 31 Aug 2026 23:51:35 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/why-openai-and-anthropic-are-buying-thousands-of-macs-for-ai/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/why-openai-and-anthropic-are-buying-thousands-of-macs-for-ai/featured-Server_room_displaying_AI_compute.jpeg" />
    </item>
    
    <item>
      <title>Google EnvHarness: A Harness for Better AI Agent Training</title>
      <link>https://www.kad8.com/ai/google-envharness-a-harness-for-better-ai-agent-training/</link>
      <pubDate>Sun, 23 Aug 2026 08:43:06 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/google-envharness-a-harness-for-better-ai-agent-training/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/google-envharness-a-harness-for-better-ai-agent-training/featured-AI_neural_network_core_visualization.jpeg" />
    </item>
    
    <item>
      <title>Why Large Language Models Reason and Behave Like Humans</title>
      <link>https://www.kad8.com/ai/why-large-language-models-speak-and-think-like-humans/</link>
      <pubDate>Fri, 21 Aug 2026 00:00:00 +0000</pubDate>
      
      <guid>https://www.kad8.com/ai/why-large-language-models-speak-and-think-like-humans/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/why-large-language-models-speak-and-think-like-humans/featured-Scaling_laws_Transformers.jpeg" />
    </item>
    
    <item>
      <title>OpenAI Pauses Frontier RL Training Over AI Safety Risks</title>
      <link>https://www.kad8.com/ai/openai-pauses-frontier-rl-training-over-ai-safety-risks/</link>
      <pubDate>Wed, 19 Aug 2026 21:42:14 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/openai-pauses-frontier-rl-training-over-ai-safety-risks/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/openai-pauses-frontier-rl-training-over-ai-safety-risks/featured-OpenAI_pauses_frontier_model_training.jpeg" />
    </item>
    
    <item>
      <title>Google&#39;s 10th-Gen TPU May Add AMD CPU Cores for AI Workloads</title>
      <link>https://www.kad8.com/ai/googles-10th-gen-tpu-may-add-amd-cpu-cores-for-ai-workloads/</link>
      <pubDate>Mon, 17 Aug 2026 21:00:04 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/googles-10th-gen-tpu-may-add-amd-cpu-cores-for-ai-workloads/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/googles-10th-gen-tpu-may-add-amd-cpu-cores-for-ai-workloads/featured-Google_partners_with_AMD.jpeg" />
    </item>
    
    <item>
      <title>OpenAI Doug Leak: Largest Pre-Training Model in Development</title>
      <link>https://www.kad8.com/ai/openai-doug-leak-largest-pre-training-model-in-development/</link>
      <pubDate>Sun, 09 Aug 2026 22:25:21 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/openai-doug-leak-largest-pre-training-model-in-development/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/openai-doug-leak-largest-pre-training-model-in-development/featured-Neural_network_pre-training.jpeg" />
    </item>
    
    <item>
      <title>AReaL 2.0 Open Source: Building Self-Evolving AI Agents with Online RL</title>
      <link>https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/</link>
      <pubDate>Fri, 03 Jul 2026 21:52:29 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/areal-2.0-open-source-building-self-evolving-ai-agents-with-online-rl/featured-AReaL_2.0_reinforcement_learning.jpeg" />
    </item>
    
    <item>
      <title>Nvidia Vera CPU: How Nvidia Is Entering the Server Computing Market</title>
      <link>https://www.kad8.com/server/nvidia-vera-cpu-how-nvidia-is-entering-the-server-computing-market/</link>
      <pubDate>Sat, 23 May 2026 21:40:44 +0800</pubDate>
      
      <guid>https://www.kad8.com/server/nvidia-vera-cpu-how-nvidia-is-entering-the-server-computing-market/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/server/nvidia-vera-cpu-how-nvidia-is-entering-the-server-computing-market/featured-Nvidia_Vera_CPU_server_processor.jpeg" />
    </item>
    
    <item>
      <title>Cursor Composer 2.5 Redefines AI Cost-Performance Economics</title>
      <link>https://www.kad8.com/ai/cursor-composer-2.5-redefines-ai-cost-performance-economics/</link>
      <pubDate>Fri, 22 May 2026 01:20:00 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/cursor-composer-2.5-redefines-ai-cost-performance-economics/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/cursor-composer-2.5-redefines-ai-cost-performance-economics/featured-Cursor_Composer_AI_coding_performance.jpeg" />
    </item>
    
    <item>
      <title>GIPO: Solving Utilization Collapse in Large-Scale RL Training</title>
      <link>https://www.kad8.com/ai/gipo-solving-utilization-collapse-in-large-scale-rl-training/</link>
      <pubDate>Mon, 18 May 2026 21:48:07 +0800</pubDate>
      
      <guid>https://www.kad8.com/ai/gipo-solving-utilization-collapse-in-large-scale-rl-training/</guid>
      <description></description>
      <media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://www.kad8.com/ai/gipo-solving-utilization-collapse-in-large-scale-rl-training/featured-GIPO_Gaussian_trust_weighting.jpeg" />
    </item>
    
  </channel>
</rss>
