Actor-Critic 方法
1. The simplest actor‑critic (QAC) 2. Advantage actor‑critic (A2C) 2.1. Baseline invariance 2.2. The algorithm of advantage actor‑critic 3. Off‑policy actor‑critic 3.1. Illustrative examples 3.2. Importance sampling 3.3. The theorem of off‑policy po…
2026/7/12 18:54:47