{"passport":{"slug":"proximal-policy-optimization-ppo","display_name":"Proximal Policy Optimization (PPO)","model_type":"multimodal","parameter_count":null,"context_window":null,"claimed_developer":"OpenAI","confirmed_developer":"OpenAI","developer_confirmed_at":"2017-07-20T00:00:00+00:00","developer_source":"Confirmed via https://openai.com/index/openai-baselines-ppo","first_appeared_at":"2026-03-05T00:30:28.301135+00:00","first_appeared_on":"rss_pipeline","status":"confirmed","availability":null,"deployment_status":"not_deployed","availability_scope":null,"gate":3,"eu_ai_act":"unknown","regulatory_status":{"eu_ai_act":"unknown"},"open_source":true,"weights_available":null,"license":"MIT (OpenAI Baselines reference implementation on GitHub)","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":"2026-03-05T00:30:28.301135+00:00","title":"First recorded in AI news","detail":"OpenAI is releasing a new class of reinforcement learning algorithms called Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.","source_url":"https://openai.com/index/openai-baselines-ppo","source_name":"OpenAI Blog"}],"delta":{"days_unattributed":null,"claimed_developer":"OpenAI","confirmed_developer":"OpenAI","match":true}}