{"id":"arxiv:1901.01753","title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","date":"2019-01-07","section":"Agents, open-endedness, AGI","quality":-0.0405,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/","source_url":"https://arxiv.org/abs/1901.01753","text_available":true,"authors":["Rui Wang","Joel Lehman","Jeff Clune","Kenneth O. Stanley"],"outgoing":[{"source":"arxiv:1901.01753","target":"arxiv:1511.05952","evidence":"title","id":"arxiv:1511.05952","title":"Prioritized Experience Replay","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c88bf0c11c1817dcc457c001dfef5cd120a0946c8a009a0fe40648dae03eb7d4/"}],"incoming":[{"source":"arxiv:1905.10985","target":"arxiv:1901.01753","evidence":"id","id":"arxiv:1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/089142f7297bed414d01b82c78dc888e4018fecff7efbe5cae66442e03f87c4b/"},{"source":"arxiv:2406.04268","target":"arxiv:1901.01753","evidence":"id","id":"arxiv:2406.04268","title":"Open-Endedness is Essential for Artificial Superhuman Intelligence","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/13964b2db9a9f793d1fcae07ca83fbe09f65454214269cac56777cb8be423a4e/"},{"source":"arxiv:2505.22954","target":"arxiv:1901.01753","evidence":"id","id":"arxiv:2505.22954","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c29f716871f80314868b5647692de387f26e12166b93bd362915fd272b6e081c/"},{"source":"arxiv:2511.07317","target":"arxiv:1901.01753","evidence":"id","id":"arxiv:2511.07317","title":"RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c0c18cb0ae7fe76a7239f38ce819c7ac588c1184dd27c5672f868ff4e2e26605/"},{"source":"arxiv:2608.19197","target":"arxiv:1901.01753","evidence":"id","id":"arxiv:2608.19197","title":"SPADE: Self-Play in Adaptive Synthetic Executable Environments","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/c524376d6034b5d79661d6f1a444591404f4a250bcb0790d802c05e02f8249df/"},{"source":"doi:10.1038/s42256-023-00754-x","target":"arxiv:1901.01753","evidence":"id","id":"doi:10.1038/s42256-023-00754-x","title":"A social path to human-like artificial intelligence","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/25e744318984a723282df54f9f39bf66e3a17e6f3b09c90a80af90c250e799be/"}],"text_parts":[{"start":0,"end":14869,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html"},{"start":14869,"end":30645,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-2.html"},{"start":30645,"end":45932,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-3.html"},{"start":45932,"end":61829,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-4.html"},{"start":61829,"end":77468,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html"},{"start":77468,"end":80447,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-6.html"}],"contents":[{"title":"Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions","offset":0,"level":1,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html#text"},{"title":"Abstract","offset":137,"level":6,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html#text"},{"title":"1 Introduction","offset":2241,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html#text"},{"title":"2 Background","offset":11655,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html#text"},{"title":"2.1 Behavioral Diversity and Stepping Stones","offset":12188,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-1.html#text"},{"title":"2.2 Open-Ended Search via Minimal Criterion Coevolution (MCC)","offset":18062,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-2.html#text"},{"title":"2.3 Evolution Strategies (ES)","offset":23173,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-2.html#text"},{"title":"3 The Paired Open-Ended Trailblazer (POET) Algorithm","offset":27549,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-2.html#text"},{"title":"4 Experiment Setup And Results","offset":34270,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-3.html#text"},{"title":"4.1 Environment and Experiment Setup","offset":35241,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-3.html#text"},{"title":"4.2 Environment Encoding and Mutation","offset":38180,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-3.html#text"},{"title":"4.3 Results","offset":42108,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-3.html#text"},{"title":"5 Discussion, Future Work, and Conclusion","offset":64751,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html#text"},{"title":"Acknowledgments","offset":72328,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html#text"},{"title":"6 Supplemental Information","offset":72780,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html#text"},{"title":"6.1 Producing New Environments","offset":73035,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html#text"},{"title":"6.2 ES-Based Transfer","offset":77441,"level":3,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-5.html#text"},{"title":"Instructions for reporting errors","offset":79483,"level":2,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/part-6.html#text"}],"text_code_points":80447,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a9790a1ede488fbbb2d7b4cdb97b884a5a1e21357b72c5e3419a83ea629d5a4b/source.md"}