What are the most common deep reinforcement learning algorithms and models apart from DQN?

Question

Recently, I have completed Atari Breakout (https://arxiv.org/pdf/1312.5602.pdf) with DQN.

Similar to DQN, what are the most common deep reinforcement learning algorithms and models in 2020? It seems that DQN is outdated and policy gradients are preferred.

Answer 1

There are several common deep reinforcement algorithms and models apart from deep Q networks (or deep Q learning). I will list some of them below (along with a link to the paper that introduced them), but note that some of these may not be state-of-the-art (at least, not anymore, and it's likely that all of these will be replaced in the future).

• Double DQN (DDQN) (2015)
• Duelling DQN (2015)
• Trust Region Policy Optimization (TRPO) (2015)
• Deep Deterministic Policy Gradient (DDPG) (2016)
• Asynchronous Advantage Actor-Critic (A3C) (2016)
• Hindsight Experience Replay (HER) (2017)
• Proximal policy optimization (PPO) (2017)
• Twin Delayed Deep Deterministic policy gradient algorithm (TD3) (2018)
• Soft Actor-Critic (SAC) (2018)

For an exhaustive overview of deep RL algorithms and models, maybe take a look at this pre-print Deep Reinforcement Learning (2018) by Yuxi Li.