Build upon your foundational Reinforcement Learning knowledge. This course covers essential intermediate techniques, including Deep Q-Networks (DQN), Policy Gradient methods, and Actor-Critic algorithms. Learn to apply function approximation and sophisticated strategies to solve more complex sequential decision-making problems. Includes hands-on implementation guides.
Prerequisites Basic Reinforcement Learning concepts.
Level:
Function Approximation
Understand why and how to use function approximators (like neural networks) in RL.
Deep Q-Networks (DQN)
Implement and understand the components of DQN, including experience replay and target networks.
DQN Variants
Learn improvements to DQN such as Double DQN and Dueling DQN.
Policy Gradient Methods
Grasp the theory behind policy gradients and implement the REINFORCE algorithm.
Actor-Critic Methods
Understand the architecture and advantages of Actor-Critic algorithms like A2C/A3C.
Algorithm Implementation
Gain practical experience implementing these intermediate RL algorithms.