1. Value-based RL
深度强化学习基础(2/5):价值学习 Value-Based Reinforcement Learning(2/5)_哔哩哔哩_bilibili
2. Policy-gradient RL
深度强化学习基础(3/5):策略学习 Policy-Based Reinforcement Learning(3/5)_哔哩哔哩_bilibili
深度强化学习基础(2/5):价值学习 Value-Based Reinforcement Learning(2/5)_哔哩哔哩_bilibili
深度强化学习基础(3/5):策略学习 Policy-Based Reinforcement Learning(3/5)_哔哩哔哩_bilibili