Wp-dyna: Planning and Reinforcement Learning in Well-plannable Environments

Reinforcement learning (RL) involves sequential decision making in uncertain environments. The aim of the decision-making agent is to maximize the benefit of acting in its environment over an extended period of time. Finding an optimal policy in RL may be very slow. To speed up learning, one often used solution is the integration of planning, for example, Sutton’s Dyna algorithm, or various other methods using macro-actions. Here we suggest to separate plannable, i.e., close to deterministic parts of the world, and focus planning efforts in this domain. A novel reinforcement learning method called WP-Dyna is proposed here. WP-Dyna builds a simple model, which is used to search for macro actions. The simplicity of the model makes planning computationally inexpensive. It is shown that WP-Dyna finds an optimal policy, and that plannable macro actions found by WP-Dyna are near-optimal. In turn, it is unnecessary to try large numbers of macro actions, which enables fast learning. The utility of WP-Dyna is demonstrated by computer simulations.