Deep Reinforcement Learning

Value-based:

• DQN : Deep Q-Network (DQN).

• DDQN : Double Deep Q-Network (Double DQN).

• DuelDQN : Dueling Deep Q-Network (Dueling DQN).

• NoisyDQN : DQN with Noisy Layers (Noisy DQN).

• PerDQN : DQN with Prioritized Experience Replay (PER DQN).

• C51 : Categorical 51 DQN (C51).

• QRDQN : DQN with Quantile Regression (QR-DQN).

• DRQN : Deep Recurrent Q-Network (DRQN).

Policy-based:

• PG : Policy Gradient (PG).

• NPG : Natural Policy Gradient (NPG).

• A2C : Advantage Actor Critic (A2C).

• PPOKL : Proximal Policy Optimization with KL Divergence (PPO-KL).

• PPOCLIP : Proximal Policy Optimization with Clipped Objective (PPO-Clip).

• PPG : Phasic Policy Gradient (PPG).

• SAC : Soft Actor-Critic (SAC).

• DDPG : Deep Deterministic Policy Gradient (DDPG).

• TD3 : Twin Delayed Deep Deterministic Policy Gradient (TD3).

• PDQN : Parameterised Deep Q-Network (P-DQN).

• MPDQN : Multi-pass Parameterised Deep Q-Network (MP-DQN).

• SPDQN : Split parameterised Deep Q-Network (SP-DQN).