Notes

🔍

AI ML>Reinforcement Learni…>Deep Reinforcement L…

Overview ◀ Map Tree Terms Read ▶ Resources Quiz Play

Deep Reinforcement Learning

25 terms

Value-Based Deep RL

7 terms

Deep Q-Network (DQN)
Experience Replay
Target Network
Double DQN
Dueling DQN
Prioritized Experience Replay
Rainbow DQN

Policy Gradient Methods

7 terms

Policy Gradient Methods
Policy Gradient Theorem
REINFORCE
Baseline (Policy Gradient)
Advantage Function
Natural Policy Gradient
Deterministic Policy Gradient (DPG)

Actor-Critic

4 terms

Actor-Critic
Advantage Actor-Critic (A2C)
Generalized Advantage Estimation (GAE)
Asynchronous Advantage Actor-Critic (A3C)

Trust Region & Modern Algorithms

7 terms

TRPO
PPO
DDPG
TD3
SAC (Soft Actor-Critic)
IMPALA
Distributional RL

Term

Open full page ↗

Loading...