Reinforcement Learning Course: Intro to Advanced Actor Critic Methods

Dive into a comprehensive 6-hour course on advanced actor-critic methods in reinforcement learning, focusing on their applications in robotics and continuous action spaces. Explore key algorithms including Actor Critic, Deep Deterministic Policy Gradients (DDPG), Twin Delayed Deep Deterministic Policy Gradients (TD3), Proximal Policy Optimization (PPO), Soft Actor Critic (SAC), and Asynchronous Advantage Actor Critic (A3C). Access provided code repositories for hands-on implementation using TensorFlow 2 and PyTorch. Gain practical insights into controlling robotic systems through electric motor actuation, while understanding the trade-offs in computational complexity. Suitable for learners with prior knowledge in reinforcement learning, this course covers software requirements and offers a detailed syllabus to guide your learning journey.

) Intro.
) Actor Critic (TF2).
) DDPG (TF2).
) TD3 (TF2).
) PPO (PyTorch).
) SAC (TF2).
) A3C (PyTorch).