“If you are interested in hot-swapping, I highly recommend OpenAI Five paper: https://arxiv.org/abs/1912.06680. It includes 10 months log of how they adapted the model to releases of Dota 2 version 7.19, 7.20, and 7.21. I agree hot-swapping is underreported, but there are some good existing reports. In fact, OpenAI Five paper today is probably more valuab…”
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as long time horizons, imperfect information, and complex, continuous state-action spaces, all challenges which will become increasingly central to more capable AI systems. OpenAI Five leveraged existing reinforcement learning techniques, scaled to learn from batches of approximately 2 million frames every 2 seconds. We developed a distributed training system and tools for continual training which allowed us to train OpenAI Five for 10 months. By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“What makes you think it is 'his' work and not theirs? I remember when OpenAI was just a joke compared to Deepmind. The turning point (as I remember) was when they used [1] deep reinforcement learning on dota2. clearly iyla (also one of the authors) contributed, but so did many others on the team I assume? [1]: https://arxiv.org/pdf/1912.06680.pdf”