Open-Endedness and AI GAs in the Era of Foundation Models скачать в хорошем качестве

Open-Endedness and AI GAs in the Era of Foundation Models

My talk at Oxford in June, 2024, including new work on OMNI-EPIC Foundation models create exciting new opportunities in our longstanding quests to produce open-ended and AI-generating algorithms, meaning agents that can truly keep learning forever. In this talk I share some of our recent work harnessing the power of foundation models to make progress in these areas, including taking advantage of different forms of being goal-conditioned. I cover our recent research: (1) OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code, (2) Video Pre-Training (VPT), and (3) Thought Cloning: Learning to Think while Acting by Imitating Human Thinking. MIT Talk Motivating and Explaining Open-endedness and AI-Generating Algorithms:    • Improving Deep Reinforcement Learning via ...   OMNI: https://arxiv.org/abs/2306.01711 OMNI-EPIC: https://arxiv.org/abs/2405.15568 Thought Cloning: https://arxiv.org/abs/2306.00323 VPT: https://openai.com/research/vpt AI-Generating Algorithms: https://arxiv.org/abs/1905.10985