https://oaklab.ai Research articles and updates from Oak Lab. en Mon, 13 Jul 2026 00:00:00 GMT https://oaklab.ai/posts/learning-from-experience-instead-of-curated-datasets.html Unlike curated datasets, experience is noisy and not fully predictable. Learning from experience requires rethinking the fundamentals of learning algorithms. Mon, 13 Jul 2026 00:00:00 GMT https://oaklab.ai/posts/learning-from-experience-instead-of-curated-datasets.html https://oaklab.ai/posts/the-oak-architecture.html Rich Sutton, The OaK Architecture: A Vision of SuperIntelligence from Experience - RLC 2025 Wed, 01 Jan 2025 00:00:00 GMT https://oaklab.ai/posts/the-oak-architecture.html https://oaklab.ai/posts/the-big-world-hypothesis.html The big world hypothesis says that in many decision-making problems the agent is orders of magnitude smaller than the environment. It can neither fully perceive the state of the world nor can it represent the value or optimal action for every state. Instead, it must learn to make sound decisions us… Mon, 01 Jan 2024 00:00:00 GMT https://oaklab.ai/posts/the-big-world-hypothesis.html