Reinforcement Learning

• Stochastic Policy Gradient Methods -- [11/2016]
• Deterministic Policy Gradient Methods -- [2/2017]
• Some research directions worth looking at -- [2/2017]
• Deep-Q Networks and Double DQN -- [2/2017]
• Fourier Basis for value function approximation -- [9/2016]
• Off Policy Eligibility Traces -- [10/2016]
• Monte Carlo Exploring starts for Blackjack -- [9/2016]
• Comparison of Qlearning and SARSA -- [9/2016]
• Comparison of Types of Eligibility traces on Maze -- [9/2016]
• Python Code for Qlearning