本文件仅用于代码归档,不属于课程原始提交文件
- 与本科课程非常相似
- hw1: Cliff Walking Environment: policy iteration/value iteration
- hw2: Cliff Walking Environment: q-learning/sarsa
- Mid-Term Test(hw3): gym-maze: DQN
- hw4: MountainCar: DQN/Double DQN
- hw5: Pendulum: DDPG/A3C
- project: 课程项目,详见project_requirements
project/project_requirements.pdf
: 课程项目要求project/report.pdf
: 课程项目报告
- gym/gymnasium
- 动手学强化学习
- Hessel M, Modayil J, Van Hasselt H, et al. Rainbow: Combining improvements in deep reinforcement learning[C]//Proceedings of the AAAI conference on artificial intelligence. 2018, 32(1).