56,966 blogs · [
{
"id": "01a087ae-2eb2-706e-a50f-5cf48c075c06",
"title": "Mini-Retirement: Or, How I Learned to Stop Grinding and Took Two Years Off",
"url": "https://neuralpensieve.github.io/2026/02/15/mini-retirement.html",
"published_at": "2026-02-15T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf48cbdf867",
"title": "The Art of Safe Policy Updates: From REINFORCE to TRPO and PPO",
"url": "https://neuralpensieve.github.io/2025/09/18/trpo-ppo-intuition.html",
"published_at": "2025-09-18T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf48d204458",
"title": "Teaching AI to Play Hokm: A Multi-Agent Reinforcement Learning Challenge",
"url": "https://neuralpensieve.github.io/2025/09/12/hokm-rl.html",
"published_at": "2025-09-12T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf48e16eb8b",
"title": "Teaching (tiny) LLMs to Play Text-Based Games Using RL (on a $300 GPU)",
"url": "https://neuralpensieve.github.io/2025/08/26/rl-llm-textworld.html",
"published_at": "2025-08-26T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf48ee6834a",
"title": "The Beautiful Intuition Behind Diffusion Models",
"url": "https://neuralpensieve.github.io/2025/07/18/diffusion-intuition.html",
"published_at": "2025-07-18T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf48fb5c99e",
"title": "How to Tame Your Deep RL",
"url": "https://neuralpensieve.github.io/2025/07/09/how-to-tame-your-deep-rl.html",
"published_at": "2025-07-09T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf49014f635",
"title": "How many words do you know?",
"url": "https://neuralpensieve.github.io/2024/12/05/vocabulary-size.html",
"published_at": "2024-12-05T00:00:00+00:00"
},
{
"id": "01a087ae-2eb2-706e-a50f-5cf490150189",
"title": "Perils and Promises of AI",
"url": "https://neuralpensieve.github.io/2024/10/20/perils-and-promises-of-ai.html",
"published_at": "2024-10-20T00:00:00+00:00"
}
] posts Claim your blog