Artificial Intelligence 2.0: The smartest combination of Double Deep Q-Learning, Policy Gradient, Actor Critic, DDPG
InstructorHadelin de Ponteves
CouponThe course provides a highly granular, 20-step approach to building the TD3 model from scratch.
Editorial course preview
This view highlights a concrete, legible example from the course presentation.
The image shows a presenter next to a screen displaying a Jupyter Notebook with Python code for reinforcement learning, training metrics, and a visual simulation of an ant agent.
Dedicated sections cover Artificial Neural Networks, Q-Learning, and Deep Q-Learning to support the main implementation.
One signal from early 2024 notes difficulties understanding the instructor's accent and reading certain mathematical formulas on video slides; however, the displayed update date does not prove these issues were addressed.
One signal from late 2022 suggests a need for more detail regarding the full training process, such as episode management and timesteps; the displayed update date does not prove this was corrected.
The curriculum aligns with the technical requirements of implementing reinforcement learning models.