{"type":"link","version":"1.0","title":"Restricting an RL-trained selection module to emit only item IDs shrinks exploration and steadies training","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/closed-action-space-stabilizes-rl-for-selection-modules","thumbnail_url":"https://ai-arch.pages.dev/og/closed-action-space-stabilizes-rl-for-selection-modules.png","thumbnail_width":1200,"thumbnail_height":630}