A comparison of action selection methods for implicit policy method reinforcement learning in continuous action-space

In this paper I investigate methods of applying reinforcement learning to continuous state- and action-space problems without a policy function. I compare the performance of four methods, one of which is the discretisation of the action-space, and the other three are optimisation techniques applied to finding the greedy action without discretisation. The optimisation methods I apply are gradient descent, Nelder-Mead and Newton's Method. The action selection methods are applied in conjunction with the SARSA algorithm, with a multilayer perceptron utilized for the approximation of the value function. The approaches are applied to two simulated continuous state- and action-space control problems: Cart-Pole and double Cart-Pole. The results are compared both in terms of action selection time and the number of trials required to train on the benchmark problems.