A Complete Reinforcement Learning System (Capstone)University of Alberta For moon landing, let’s build a complete Deep RL system. You will get hands dirty in an expected SARSA agent using neural networks as function approximation and Adam as optimizer, also don’t forget softmax and replay buffer, and later parameter study! What an achievement! But meanwhile – as Prof. Martha White and Prof. Adam White pointed out – this is only the “first step towards learning … Continue reading My #41 course certificate from Coursera