OpenAI Five 基準測試結果
OpenAI Five Benchmark: Results
OpenAI Five 昨日以三局兩勝制擊敗一隊排名位於第 99.95 百分位的 Dota 玩家。對手是 Blitz、Cap、Fogged、Merlini 和 MoonMeander,其中四人曾職業參與 Dota;比賽有現場觀眾,直播同時有 100,000 名觀眾觀看。
這場三局兩勝賽呈現 OpenAI Five 對陣 99.95 百分位 Dota 玩家時的直接結果,亦交代對手中有四人曾以職業身份參與 Dota。
Our usual development cycle is to train each major revision of the system from scratch. However, this version of OpenAI Five contains parameters that have been training since June 9th across six major system revisions. Each revision was initialized with parameters from the previous one.
We invested heavily in “surgery” tooling which allows us to map old parameters to a new network architecture. For example, when we first trained warding, we shared a single action head for determining where to move and where to place a ward. But Five would often drop wards seemingly in the direction it was trying to go, and we hypothesized it was allocating its capacity primarily to movement. Our tooling let us split the head into two clones initialized with the same parameters.
We estimate that we used the following amounts of compute to train our various Dota systems:
We are also releasing our latest network architecture(opens in a new window).
來源:OpenAI News · openai.com