Afterstate on PANG Kaicheng's Homepage http://pangkaicheng.com/tags/afterstate/ Recent content in Afterstate on PANG Kaicheng's Homepage Hugo en-us Tue, 11 Nov 2025 00:00:00 +0000 Temporal Difference (TD) Control Algorithms Comparison: SARSA, Expected SARSA, and Q-learning http://pangkaicheng.com/blog/comparision-of-three-td-method-approximation/ Tue, 11 Nov 2025 00:00:00 +0000 http://pangkaicheng.com/blog/comparision-of-three-td-method-approximation/ Comparative analysis of major one-step Temporal Difference (TD) control algorithms: SARSA, Expected SARSA, and Q-learning, focusing on their policy nature and target construction. Reinforcement Learning for Outfit Compatibility http://pangkaicheng.com/blog/reinforcement-learning-for-outfit/ Mon, 15 Sep 2025 00:00:00 +0000 http://pangkaicheng.com/blog/reinforcement-learning-for-outfit/ Modeling the outfit compatibility problem as a Markov Decision Process (MDP), defining the state space, action space, and afterstate formulation for sequential item selection. Afterstate Formulation http://pangkaicheng.com/blog/afterstate-formulation/ Sun, 01 Sep 2024 00:00:00 +0000 http://pangkaicheng.com/blog/afterstate-formulation/ Formalization of the afterstate concept in Reinforcement Learning, including value functions and Dynamic Programming / Temporal Difference algorithms.