Project1 topics: Imitation Learning - Behavior Cloning - Dagger - CMA-ES
Project2 topics: Value Iteration - Policy Iteration - DQN - DoubleDQN - DuelDQN
Project3 topics: REINFORCE - Actor-Critic network
Project4 topics: Deep Deterministic Policy Gradient (DDPG)- Hindisght Experience Replay (HER)
Project5 topics: Model-Based Reinforcement Learning with Probabilistic Ensemble and Trajectory Sampling (PETS)