{"work":{"id":"b047dc18-e9a3-4d11-8ff6-cd59d41a6357","openalex_id":null,"doi":null,"arxiv_id":"1912.06680","raw_key":null,"title":"Dota 2 with Large Scale Deep Reinforcement Learning","authors":null,"authors_text":"OpenAI: Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemys{\\l}aw D\\k{e}biak, Christy Dennison","year":2019,"venue":"cs.LG","abstract":"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.","external_url":"https://arxiv.org/abs/1912.06680","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-20T14:08:21.026975+00:00","pith_arxiv_id":"1912.06680","created_at":"2026-05-09T06:40:40.856610+00:00","updated_at":"2026-05-20T14:08:21.026975+00:00","title_quality_ok":true,"display_title":"Dota 2 with Large Scale Deep Reinforcement Learning","render_title":"Dota 2 with Large Scale Deep Reinforcement Learning"},"hub":{"state":{"work_id":"b047dc18-e9a3-4d11-8ff6-cd59d41a6357","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":43,"external_cited_by_count":null,"distinct_field_count":8,"first_pith_cited_at":"2021-02-02T04:07:38+00:00","last_pith_cited_at":"2026-05-19T07:54:40+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-20T16:51:58.298085+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":12},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":12},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}