Reinforcement Learning 10: On-policy Control with Approximation Jan 31, 2019 10 On-policy Control with Approximation 10.1 Episodic Semi-gradient Control Example 10.1: Mountain Car Task 10.2 Semi-gradient n-step Sarsa 10.3 Average Reward: A New Problem Setting for Continuing 10.4 Deprecating the Discounted Setting 10.5 Differential Semi-gradient n-step Sarsa 10.6 Summary