强化学习必修课：引领人工智能新时代

强化学习必修课：引领人工智能新时代资料.png  [493.5 KB]
2_3-2-conda使用命令.mp4  [11.9 MB]
4_3-4-仿真环境Gym安装.mp4  [19.0 MB]
5_10-5-MBPO的代码实现.mp4  [53.8 MB]
6_9-6-软性演员评论家算法.mp4  [38.6 MB]
7_6-7-Q-Learning&SARSA代码实现.mp4  [23.8 MB]
2_11-2-博弈论与强化学习.mp4  [64.7 MB]
3_4-3-马尔可夫决策过程：试着-“干”.mp4  [29.6 MB]
3_2-3-概率.mp4  [46.6 MB]
2_10-2-Dyna-Q算法.mp4  [44.6 MB]
7_9-7-SAC代码实现.mp4  [35.1 MB]
3_5-3-价值迭代.mp4  [19.2 MB]
4_10-4-基于模型的策略优化.mp4  [19.7 MB]
2_1-2-认识强化学习.mp4  [53.8 MB]
1_10-1-基于模型的强化学习核心思想和原理.mp4  [48.0 MB]
4_9-4-深度确定性策略梯度.mp4  [30.3 MB]
5_11-5-AlphaStar系统.mp4  [82.4 MB]
8_4-8-马尔可夫过程代码实现.mp4  [40.2 MB]
6_11-6-基于人类反馈大强化学习.mp4  [47.1 MB]
2_5-2-策略迭代.mp4  [40.0 MB]
1_11-1模仿学习.mp4  [48.4 MB]
3_11-3-多智能体强化学习.mp4  [44.4 MB]
5_3-5-深度学习库PyTorch的安装.mp4  [9.2 MB]
2_12-2-项目实战：大模型RLHF.mp4  [31.4 MB]
4_4-4-马尔可夫奖励过程：懂得“想”.mp4  [49.4 MB]
3_7-3-常见问题改进和扩展.mp4  [27.5 MB]
3_9-3-演员评论家算法代码实现.mp4  [19.7 MB]
5_6-5-Q-Learning算法.mp4  [32.3 MB]
3_8-3-策略梯度方法代码实现.mp4  [19.4 MB]
4_5-4-动态规划代码实现.mp4  [43.5 MB]
3_10-3-Dyna-Q算法代码实现.mp4  [17.7 MB]
4_7-4-DQN改进算法代码实现.mp4  [31.0 MB]
4_12-4-下一步的学习建议.mp4  [33.3 MB]
5_9-5-DDPG算法代码实现.mp4  [22.5 MB]
2_9-2-改进型演员评论家算法.mp4  [23.0 MB]
7_4-7-常见问题解析.mp4  [21.7 MB]
3_12-3-强化学习最新发展趋势.mp4  [65.6 MB]
5_8-5-近端策略优化（PPO）代码实现.mp4  [34.6 MB]
4_11-4-MADDP的代码实现.mp4  [45.1 MB]
1_9-1-演员评论家算法核心思想和原理.mp4  [20.1 MB]
6_6-6-SARSA算法.mp4  [20.8 MB]
3_1-3-课程使用的技术栈.mp4  [12.0 MB]
1_3-1-CUDA+Anaconda深度学习环境配置.mp4  [18.7 MB]
2_4-2-马尔可夫观测过程：学会“看”.mp4  [40.9 MB]
3_6-3-蒙特卡洛方法和时序差分代码实现.mp4  [22.8 MB]
5_4-5-贝尔曼方程：迭代求解价值函数.mp4  [30.6 MB]
1_7-1-深度Q网络核心思想和原理.mp4  [44.7 MB]
2_6-2-时序差分方法.mp4  [34.2 MB]
1_8-1-策略梯度核心思想和原理.mp4  [44.2 MB]
1_5-1-动态回归核心思想和原理.mp4  [30.9 MB]
4_8-4-近端策略优化算法.mp4  [36.2 MB]
1_2-1-线性代数.mp4  [26.9 MB]
2_8-2-蒙特卡洛策略梯度.mp4  [24.2 MB]
1_12-1-项目实战：Gym游戏.mp4  [51.4 MB]
4_6-4-广义策略迭代.mp4  [19.6 MB]
3_3-3-Jupyter-Notebook快速上手.mp4  [14.1 MB]
2_2-2-微积分.mp4  [30.0 MB]
6_4-6-模型分类与选择.mp4  [30.8 MB]
1_4-1-序列建模与概率图模型.mp4  [38.1 MB]
2_7-2-DQN-代码实现.mp4  [35.8 MB]
1_6-1-蒙特卡洛方法.mp4  [32.5 MB]
1_1-1-课程内容和理念.mp4  [59.0 MB]