#off-policy reinforcement learning

Off-Policy Reinforcement Learning: 1 AI articles covering off-policy reinforcement learning news, analysis, and research

Articles

Regularized Emphatic Temporal-Difference Learning: StabilityNEW⭐9

📅 2小时前👁 4 views

Regularized emphatic TD (RETD) restores stability of off-policy TD learning under constant stepsizes, with convergence guarantees and 10,000-run experiments val...