RL_sysu_homework

Homework with respect to Reinforcement Learning for SYSU graduate students

---

homework1:

1. value iteration and policy iteration (policy evaluation and policy improvement)
2. Tabular Q-Learning
3. Sarsa and Q-learning

homework2

1. DQN for PongNoFrameskip-v4
2. REINFORCE and REINFORCE with baseline for CartPole-v0
3. DDPG (TD3) for LunarLanderContinuous-v2
4. DDPG (TD3) for BipedalWalker-v2

homework3

• Multi-Agent DRL algorithms for Multi-Agent Particle Environments (MPE) (simple_spread), including VDN, QMIX and MATD3.