Reinforcement learning agents Beyond DQN (policy Gradient)

Up to this moment, we covered most popular tutorials related to DQN - value-based reinforcement learning algorithms. In deep reinforcement learning, deep Q-learning Networks are relatively simple. To their credit, not only DQN's are comparatively simple, but there are many other deep RL agents that also make efficient use of the training samples that are available to them. That said, DQN agents do have drawbacks. Most notable are: DQN can become intractable to estimate the optimal Q-value and DQN's are not