{"passport":{"slug":"ucb-exploration-via-q-ensembles","display_name":"UCB exploration via Q-ensembles","model_type":"game","parameter_count":null,"context_window":null,"claimed_developer":"OpenAI","confirmed_developer":"OpenAI","developer_confirmed_at":"2017-06-05T00:00:00+00:00","developer_source":"Confirmed via https://arxiv.org/abs/1706.01502","first_appeared_at":"2026-03-05T00:30:47.986311+00:00","first_appeared_on":"rss_pipeline","status":"confirmed","availability":null,"deployment_status":"not_deployed","availability_scope":null,"gate":3,"eu_ai_act":"GPAI","regulatory_status":{"eu_ai_act":"GPAI"},"open_source":true,"weights_available":null,"license":null,"provenance_chain":[],"parent_model":null,"model_family":null,"superseded_by":null,"supersedes":[],"recommended_replacement":null,"product_links":null},"events":[{"event_type":"first_appearance","event_date":"2026-03-05T00:30:47.986311+00:00","title":"First recorded in AI news","detail":"OpenAI has released a new exploration method called UCB (Upper Confidence Bound) exploration via Q-ensembles, which aims to improve the exploration-exploitation tradeoff in reinforcement learning.","source_url":"https://openai.com/index/ucb-exploration-via-q-ensembles","source_name":"OpenAI Blog"}],"delta":{"days_unattributed":null,"claimed_developer":"OpenAI","confirmed_developer":"OpenAI","match":true}}