Deep Reinforcement Learning (Fall 2018)

Project 1: Value Based RL Methods Including Deep Q-Network (DQN) and Double Deep Q-Network (DDQN)
https://medium.com/@amitp-ai/double-dqn-48562b5f31c1

Project 2: Policy Based RL Methods Including Advantage Actor-Critic (A2C) and Deep Deterministic Policy Gradient (DDPG)
https://medium.com/@amitp-ai/policy-gradients-1edbbbc8de6b

Project 3: Multi-Agent RL Methods Such as Multi-Agent DDPG (MADDPG)
https://medium.com/@amitp-ai/maddpg-91caa221d75e